Arrow Research search

Author name cluster

Xin Liu

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

113 papers
2 author rows

Possible papers

113

AAAI Conference 2026 Conference Paper

Collaborative Feature Matching with Progressive Correspondence Learning

  • Xin Liu
  • Yanbing Han
  • Rong Qin
  • Bing Wang
  • Jufeng Yang

Accurate feature matching between image pairs is fundamental for various computer vision applications. In detector-base process, the feature matcher aims to find the optimal feature correspondences, and the match filter is used for further removing mismatches. However, their connection is rarely exploited since they are usually treated as two separate issues in previous method, which may lead to suboptimal results. In this paper, we propose an end-to-end collaborative feature matching (CFM) method, which contains a keypoint learning (KL) module and a correspondence learning (CL) module, to bridge the gap between two types of works. The former improves the discrimination of keypoints, and provides high-quality dynamic matches for CL module. The latter further captures the rich context of matches, and gives effective feedback to KL module. These two modules can reinforce each other in a progressive manner. Besides, we develop an efficient version of CFM, named ECFM, using an adaptive sampling strategy to avoid the negative influence of uninformative keypoints. Experimental results indicate that both methods outperform the state-of-the-art competitors in the tasks of relative pose estimation and visual localization.

PDF Details DOI

AAAI Conference 2026 Conference Paper

C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation

  • Yu Li
  • Zhe Yang
  • Yi Huang
  • Xin Liu
  • Guilin Qi

Recent advancements in large language models (LLMs) have demonstrated remarkable text generation capabilities. However, controlling specific attributes of generated text remains challenging without architectural modifications or extensive fine-tuning. Current methods typically toggle a single, basic attribute but struggle with precise multi-attribute control. In scenarios where attribute requirements conflict, existing methods lack coordination mechanisms, causing interference between desired attributes. Furthermore, these methods fail to incorporate iterative optimization processes in the controlled generation pipeline. To address these limitations, we propose Conflict-aware, Composite, and Collaborative Controlled Text Generation (C³TG), a two-phase framework for fine-grained, multi-dimensional text attribute control. During generation, C³TG selectively pairs the LLM with the required attribute classifiers from the 17 available dimensions and employs weighted KL-divergence to adjust token probabilities. The optimization phase then leverages an energy function combining classifier scores and penalty terms to resolve attribute conflicts through iterative feedback, enabling precise control over multiple dimensions simultaneously while preserving natural text flow. Experiments show that C³TG significantly outperforms baselines across multiple metrics including attribute accuracy, linguistic fluency, and output diversity, while simultaneously reducing toxicity. These results establish C³TG as an effective and flexible solution for multi-dimensional text attribute control that requires no costly model modifications.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DRFGD: Disentangled Representation-Focused Generative Defense for Attack-Tolerant Cross-Modal Hashing

  • Zhongqing Yu
  • Xin Liu
  • Yiu-ming Cheung
  • Zhikai Hu
  • Wentao Fan
  • Pan Zhou

With the widespread deployment of cross-modal retrieval in real-world scenarios, ensuring robustness against adversarial attacks is increasingly critical. Remarkably, deep cross-modal hashing is highly vulnerable to adversarial attacks due to its discrete nature and low-dimensional hash codes, while existing defense methods often fail to suppress perturbations embedded in vulnerable features and lack the capacity to model modality-specific structural differences, resulting in suboptimal adversarial robustness. To address these challenges, we propose a novel Disentangled Representation-Focused Generative Defense (DRFGD) framework for attack-tolerant cross-modal hashing. Without altering the structure of retrieval model, DRFGD defends against adversarial attacks by disentangling input representations into adversarial-robust and adversarial-vulnerable components, by an efficient dual-branch semantic-aware encoder. Guided by such disentangled robust features, an attack-tolerant generative module is seamlessly designed to synthesize semantically aligned and perturbation-resilient examples for robust adversarial training, thereby significantly promoting collaborative defense robustness to attackers. Consequently, the semantically consistent hash codes can be well obtained to enhance adversarial robustness in complex cross-modal attacking scenarios. Extensive experiments on public benchmarks demonstrate that DRFGD substantially improves retrieval robustness under various attacking scenarios, and shows its improved defense performance in comparison with the SOTA works.

PDF Details DOI

AAAI Conference 2026 Conference Paper

EdGCL: Disentangling Social and Cognitive Homophily in Graph-Based Educational Recommender Systems

  • Qingqing Liang
  • Chunyang Wang
  • Peiwei Xia
  • Yanan Zeng
  • Xin Liu
  • Xuesong Lu
  • Aoying Zhou

Educational recommendation systems have been a fundamental component for alleviating learning disorientation in self-paced learning. While existing studies mainly leverage cognitive theories to guide learning motivation modeling, they critically overlook the role of social influences. Through empirical analysis, we identify social homophily as an additional driver of learning behaviors, i.e., learners tend to adopt resources validated by their social cohort. However, two challenges impede effective social homophily modeling: (1) the absence and sparsity of predefined social relations in online education, and (2) the deep entanglement of social homophily with cognitive homophily in behavioral data. To tackle these challenges, we propose a graph-based framework EdGCL that explicitly disentangles social homophily and cognitive homophily. EdGCL infers implicit social relations from learners' social behaviors and encodes them via a graph transformer, generating social-view representations. Simultaneously, it constructs a heterogeneous learning graph to model cognitive homophily, which is enhanced by a type-aware aggregator and cognitive diagnosis loss. To ensure the semantic distinctiveness of dual-view homophily modeling, a cross-view contrastive disentanglement mechanism is designed to pull intra-view representations closer while pushing inter-view representations away. Evaluation on two real-world educational datasets demonstrates the superior recommendation performance of EdGCL, highlighting the necessity of dual homophily modeling for understanding the motivations behind learning behaviors.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Enhancing Rotation-Invariant 3D Learning with Global Pose Awareness and Attention Mechanisms

  • Jiaxun Guo
  • Manar Amayri
  • Nizar Bouguila
  • Xin Liu
  • Wentao Fan

Recent advances in rotation-invariant (RI) learning for 3D point clouds typically replace raw coordinates with handcrafted RI features to ensure robustness under arbitrary rotations. However, these approaches often suffer from the loss of global pose information, making them incapable of distinguishing geometrically similar but spatially distinct structures. We identify that this limitation stems from the restricted receptive field in existing RI methods, leading to Wing–tip feature collapse, a failure to differentiate symmetric components (e.g., left and right airplane wings) due to indistinguishable local geometries. To overcome this challenge, we introduce the Shadow-informed Pose Feature (SiPF), which augments local RI descriptors with a globally consistent reference point (referred to as the “shadow”) derived from a learned shared rotation. This mechanism enables the model to preserve global pose awareness while maintaining rotation invariance. We further propose Rotation-invariant Attention Convolution (RIAttnConv), an attention-based operator that integrates SiPFs into the feature aggregation process, thereby enhancing the model’s capacity to distinguish structurally similar components. Additionally, we design a task-adaptive shadow locating module based on the Bingham distribution over unit quaternions, which dynamically learns the optimal global rotation for constructing consistent shadows. Extensive experiments on 3D classification and part segmentation benchmarks demonstrate that our approach substantially outperforms existing RI methods, particularly in tasks requiring fine-grained spatial discrimination under arbitrary rotations.

PDF Details DOI

AIJ Journal 2026 Journal Article

ExPred: Explainable stock movement prediction via hybrid reflection and direct preference hierarchical optimization

  • Shuqi Li
  • Heyue Lin
  • Xin Liu
  • Rui Yan

• We introduce ExPred, a framework for explainable stock movement prediction that forecasts future stock movements from stock-related textual information while simultaneously providing interpretable and reasonable explanations. • To address the limitation of discarding hard samples in previous automated labeling methods, we propose a Hybrid Reflection Agent (HRA). By incorporating a supervised-reflection mechanism, HRA recovers challenging samples and automatically generates preferred and dispreferred completions, significantly enriching the training data for advanced preference optimization. • To explicitly balance prediction accuracy and explanation quality, we propose Direct Preference Hierarchical Optimization (DPHO), which fine-tunes LLMs hierarchically at both sentence and token levels. Token-level optimization emphasizes prediction correctness, while sentence-level optimization targets the overall quality and coherence of explanations. Stock prices are driven by multifactor influences, making it difficult to pinpoint the exact cause of price movements. While Large Language Models (LLMs) offer a promising path toward explainable stock prediction, existing frameworks face two critical limitations. First, although recent methods have automated data annotation via self-reflection, they typically discard “hard samples” that the model fails to self-correct, leading to biased training data that lacks coverage of complex market scenarios. Second, treating prediction accuracy and explanation quality as equally weighted objectives ignores their inherent hierarchy: an explanation is meaningful only when the corresponding prediction is accurate. To address these gaps, we propose ExPred, a novel framework integrated with a Hybrid Reflection Agent (HRA) and a Direct Preference Hierarchical Optimization (DPHO) algorithm. To improve data coverage, HRA incorporates a supervised-reflection loop alongside self-reflection, injecting teacher signals to recover hard samples and automatically generating preferred versus dispreferred completion pairs. Building on these pairs, DPHO hierarchically fine-tunes the LLM by explicitly prioritizing prediction correctness via token-level optimization, while refining explanation coherence at the sentence level. Experiments on real-world datasets demonstrate that ExPred successfully aligns these dual objectives, significantly outperforming state-of-the-art baselines in both prediction accuracy and explanation quality. Our code is available at https: //github. com/Shuqi-li/ExPred.

Details DOI

AAAI Conference 2026 Conference Paper

Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models

  • Xin Liu
  • Qiyang Song
  • Qihang Zhou
  • Haichao Du
  • Shaowen Xu
  • Wenbo Jiang
  • Weijuan Zhang
  • Xiaoqi Jia

Large language models (LLMs) increasingly support multilingual understanding and generation. Meanwhile, efforts to interpret their internal mechanisms have emerged, offering insights to enhance multilingual performance. While multi-head self-attention (MHA) has proven critical in many areas, its role in multilingual capabilities remains underexplored. In this work, we study the contribution of MHA in supporting multilingual processing in LLMs. We propose Language Attention Head Importance Scores (LAHIS), an effective and efficient method that identifies attention head importance for multilingual capabilities via a single forward and backward pass through the LLM. Applying LAHIS to Aya-23-8B, Llama-3.2-3B, and Mistral-7B-v0.1, we reveal the existence of both language-specific and language-general heads. Language-specific heads enable cross-lingual attention transfer to guide the model toward target language contexts and mitigate off-target language generation issue, contributing to addressing challenges in multilingual LLMs. We also introduce a lightweight adaptation that learns a soft head mask to modulate attention outputs over language heads, requiring only 20 tunable parameters to improve XQuAD accuracy. Overall, our work enhances both the interpretability and multilingual capabilities of LLMs from the perspective of MHA.

PDF Details DOI

EAAI Journal 2026 Journal Article

Intelligent control framework for Unmanned Aerial Vehicle autonomous docking based on Linear Active Disturbance Rejection Control and improved Particle Swarm Optimization

  • Mingzhi Shao
  • Xin Liu
  • Wenchao Cui
  • Chengmeng Sun
  • Haiwen Yuan

Autonomous aerial docking of Unmanned Aerial Vehicle (UAV) is essential for aerial refueling, payload replacement, and cooperative operations, yet existing methods often exhibit low docking accuracy, weak disturbance rejection, and empirical parameter tuning. To overcome these limitations, this study proposes an intelligent control framework that integrates Linear Active Disturbance Rejection Control (LADRC) with an Improved Particle Swarm Optimization (IPSO) algorithm. First, a six degree of freedom dynamic model of the UAV and cone sleeve system is developed, incorporating wind disturbance, turbulence, and parameter perturbations. Second, the LADRC method realizes decoupled control of altitude, lateral, and velocity channels, ensuring robust dynamic compensation. Third, the IPSO algorithm, an Artificial Intelligence (AI) based optimization approach, is employed to adaptively tune the controller bandwidth and observer gains. This AI enhanced parameter learning process improves the generalization capability of LADRC under varying flight conditions. Simulation and scaled flight experiments demonstrate that the proposed AI driven LADRC achieves stable docking under fifty percent perturbations, with a trajectory root mean square error of 0. 04 m and a relative velocity error of 0. 03 m per second. Compared with conventional controllers, the tracking error is reduced by up to 38 percent. These results confirm that combining LADRC with AI based optimization offers a robust and precise solution for UAV autonomous aerial docking in complex and uncertain environments.

Details DOI

AAAI Conference 2026 Conference Paper

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference

  • Yuxuan Tian
  • Zihan Wang
  • Yebo Peng
  • Aomufei Yuan
  • Zhiming Wang
  • Bairen Yi
  • Xin Liu
  • Yong Cui

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which leads to information loss and hallucinations. Recently, merging-based strategies have been explored to retain more information by merging KV pairs that would be discarded; however, these existing approaches inevitably introduce inconsistencies in attention distributions before and after merging, causing degraded generation quality. To overcome this challenge, we propose KeepKV, a novel adaptive KV cache merging method designed to preserve performance under strict memory constraints, achieving single-step lossless compression and providing error bounds for multi-step compression. KeepKV introduces the Electoral Votes mechanism that records merging history and adaptively adjusts attention scores. Moreover, it further leverages a novel Zero Inference-Perturbation Merging method, compensating for attention loss resulting from cache merging. Extensive experiments on various benchmarks and LLM architectures demonstrate that KeepKV substantially reduces memory usage while successfully retaining essential context information, achieving over 2 times inference throughput improvement and maintaining superior generation quality even with only 10% KV cache budgets.

PDF Details DOI

AAAI Conference 2026 Conference Paper

OmniScale: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

  • Qianli Ma
  • Yaowei Zheng
  • Zhelun Shi
  • Zhongkai Zhao
  • Bin Jia
  • Ziyue Huang
  • Zhiqi Lin
  • Youjie Li

Recent advances in large language models (LLMs) have driven impressive progress in omni-modal understanding and generation. However, training omni-modal LLMs remains a significant challenge due to the heterogeneous model architectures required to process diverse modalities, necessitating sophisticated system design for efficient large-scale training. Existing frameworks typically entangle model definition with parallel logic, incurring limited scalability and substantial engineering overhead for end-to-end omni-modal training. We present OmniScale, a modular and efficient training framework to accelerate the development of omni-modal LLMs. OmniScale introduces model-centric distributed recipes that decouples communication from computation, enabling efficient 3D parallelism on omni-modal LLMs. OmniScale also features a flexible configuration interface supporting seamless integration of new modalities with minimal code change. Using OmniScale, a omni-modal mixture-of-experts (MoE) model with 30B parameters can be trained with over 2,800 tokens/sec/GPU throughput and scale to 160K context lengths via 3D parallelism on 128 GPUs, showcasing its superior efficiency and scalability for training large omni-modal LLMs.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Role Perceptual Augmented Temporal Graph Network for Related-party Transaction Detection

  • Xin Liu
  • Yuanhang Yu
  • Peng Zhu
  • Dawei Cheng
  • Changjun Jiang

Illegal related-party transactions (RPT) are federal felonies that pose a severe threat to the stability and integrity of modern financial systems. The increasing frequency of RPTs forms complex and dynamic networks. Existing temporal graph learning methods tend to treat entities as functionally homogeneous, ignoring the diverse and evolving structural roles of nodes. Role-based embedding methods model global structure by bridging same-role nodes, but their reliance on a unified mechanism for aggregation and evolution means they fail to distinguish the underlying logic of distinct interactions governed by structural roles. The limitations motivate us to develop a customized role-based strategy. It can also adapt to evolving RPT dynamics, thereby forming a continuous regulatory process to combat illegal activities. In this paper, we propose an innovative Role Perceptual Augmented Temporal Graph Network (RPATGN) for proactive RPT detection. We analyze the structural roles of nodes and employ a role-based message passing mechanism that adapts its aggregation strategy based on the roles of interacting nodes. We integrate a variational graph recurrent neural network, enhanced by temporal contextual attention, to explicitly model the dynamics of the roles and the overall network evolution. Extensive experiments on real-world financial datasets demonstrate the effectiveness of our approach for RPT detection. It holds practical significance for fostering robust financial systems and promoting healthy, transparent financial markets.

PDF Details DOI

AAAI Conference 2025 Conference Paper

A Comprehensive Overhaul of Multimodal Assistant with Small Language Models

  • Minjie Zhu
  • Yichen Zhu
  • Ning Liu
  • Xin Liu
  • Zhiyuan Xu
  • Chaomin Shen
  • Yaxin Peng

Multimodal Large Language Models (MLLMs) have showcased impressive skills in tasks related to visual understanding and reasoning. Yet, their widespread application faces obstacles due to the high computational demands during both the training and inference phases, restricting their use to a limited audience within the research and user communities. In this paper, we investigate the design aspects of Multimodal Small Language Models (MSLMs) and propose an efficient multimodal assistant named Mipha, which is designed to create synergy among various aspects: visual representation, language models, and optimization strategies. We show that without increasing the volume of training data, our Mipha-3B outperforms the state-of-the-art large MLLMs, especially LLaVA-1.5-13B, on multiple benchmarks. Through detailed discussion, we provide insights and guidelines for developing strong MSLMs that rival the capabilities of MLLMs.

PDF Details DOI

JMLR Journal 2025 Journal Article

A Decentralized Proximal Gradient Tracking Algorithm for Composite Optimization on Riemannian Manifolds

  • Lei Wang
  • Le Bao
  • Xin Liu

This paper focuses on minimizing a smooth function combined with a nonsmooth regularization term on a compact Riemannian submanifold embedded in the Euclidean space under a decentralized setting. Typically, there are two types of approaches at present for tackling such composite optimization problems. The first, subgradient-based approaches, rely on subgradient information of the objective function to update variables, achieving an iteration complexity of $O(\epsilon^{-4}\log^2(\epsilon^{-2}))$. The second, smoothing approaches, involve constructing a smooth approximation of the nonsmooth regularization term, resulting in an iteration complexity of $O(\epsilon^{-4})$. This paper proposes a proximal gradient type algorithm that fully exploits the composite structure. The global convergence to a stationary point is established with a significantly improved iteration complexity of $O(\epsilon^{-2})$. To validate the effectiveness and efficiency of our proposed method, we present numerical results from real-world applications, showcasing its superior performance compared to existing approaches. [abs] [ pdf ][ bib ] &copy JMLR 2025. ( edit, beta )

PDF Details

AIJ Journal 2025 Journal Article

A simple yet effective self-debiasing framework for transformer models

  • Xiaoyue Wang
  • Xin Liu
  • Lijie Wang
  • Suhang Wu
  • Jinsong Su
  • Hua Wu

Current Transformer-based natural language understanding (NLU) models heavily rely on dataset biases, while failing to handle real-world out-of-distribution (OOD) instances. Many methods have been proposed to deal with this issue, but they ignore the fact that the features learned in different layers of Transformer-based NLU models are different. In this paper, we first conduct preliminary studies to obtain two conclusions: 1) both low- and high-layer sentence representations encode common biased features during training; 2) the low-layer sentence representations encode fewer unbiased features than the highlayer ones. Based on these conclusions, we propose a simple yet effective self-debiasing framework for Transformer-based NLU models. Concretely, we first stack a classifier on a selected low layer. Then, we introduce a residual connection that feeds the low-layer sentence representation to the top-layer classifier. In this way, the top-layer sentence representation will be trained to ignore the common biased features encoded by the low-layer sentence representation and focus on task-relevant unbiased features. During inference, we remove the residual connection and directly use the top-layer sentence representation to make predictions. Extensive experiments and indepth analyses on NLU tasks show that our framework performs better than several competitive baselines, achieving a new SOTA on all OOD test sets.

Details DOI

ECAI Conference 2025 Conference Paper

AIRES: A General Framework for Efficient Intrinsic Rewards Based on Attention Mechanisms

  • Xin Liu
  • Jie Tan
  • Li Shen
  • Xu Wang
  • Guoli Wu
  • Xiaoguang Ren
  • Huadong Dai

Efficient exploration in high-dimensional observation spaces remains a critical challenge in deep reinforcement learning, particularly in scenarios with sparse extrinsic rewards. A promising approach is to encourage exploration by estimating intrinsic rewards based on the novelty of observations. However, there is a gap between the observed novelty and the actual effectiveness of exploration, as both environmental stochasticity and the agent’s actions may influence observations. To accurately evaluate the novelty contributed by agent exploration in intrinsic rewards, we propose the AIRES (Attention-driven Intrinsic Reward for Exploration Strategy) framework. AIRES leverages the attention mechanisms to analyze the relationship within trajectory sequences generated by agent-environment interactions, employing attention weights to quantify the relevance of observations to actions. By applying attention weights to intrinsic rewards, the novelty brought by agent exploration is enhanced and the impact of environmental stochasticity is reduced. Extensive experiments demonstrate that AIRES significantly enhances the performance of prominent intrinsic reward methods, establishing it as a robust and scalable solution for efficient exploration.

Details

JBHI Journal 2025 Journal Article

BINDTI: A Bi-Directional Intention Network for Drug-Target Interaction Identification Based on Attention Mechanisms

  • Lihong Peng
  • Xin Liu
  • Long Yang
  • Longlong Liu
  • Zongzheng Bai
  • Min Chen
  • Xu Lu
  • Libo Nie

The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i. e. , CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery.

Details DOI

JBHI Journal 2025 Journal Article

CodePhys: Robust Video-Based Remote Physiological Measurement Through Latent Codebook Querying

  • Shuyang Chu
  • Menghan Xia
  • Mengyao Yuan
  • Xin Liu
  • Tapio Seppänen
  • Guoying Zhao
  • Jingang Shi

Remote photoplethysmography (rPPG) aims to measure non-contact physiological signals from facial videos, which has shown great potential in many applications. Most existing methods directly extract video-based rPPG features by designing neural networks for heart rate estimation. Although they can achieve acceptable results, the recovery of rPPG signal faces intractable challenges when interference from real-world scenarios takes place on facial video. Specifically, facial videos are inevitably affected by non-physiological factors (e. g. , camera device noise, defocus, and motion blur), leading to the distortion of extracted rPPG signals. Recent rPPG extraction methods are easily affected by interference and degradation, resulting in noisy rPPG signals. In this paper, we propose a novel method named CodePhys, which innovatively treats rPPG measurement as a code query task in a noise-free proxy space (i. e. , codebook) constructed by ground-truth PPG signals. We consider noisy rPPG features as queries and generate high-fidelity rPPG features by matching them with noise-free PPG features from the codebook. Our approach also incorporates a spatial-aware encoder network with a spatial attention mechanism to highlight physiologically active areas and uses a distillation loss to reduce the influence of non-periodic visual interference. Experimental results on four benchmark datasets demonstrate that CodePhys outperforms state-of-the-art methods in both intra-dataset and cross-dataset settings.

Details DOI

AAAI Conference 2025 Conference Paper

CohEx: A Generalized Framework for Cohort Explanation

  • Fanyu Meng
  • Xin Liu
  • Zhaodan Kong
  • Xin Chen

eXplainable Artificial Intelligence (XAI) has garnered significant attention for enhancing transparency and trust in machine learning models. However, the scopes of most existing explanation techniques focus either on offering a holistic view of the explainee model (global explanation) or on individual instances (local explanation), while the middle ground, i.e., cohort-based explanation, is less explored. Cohort explanations offer insights into the explainee's behavior on a specific group or cohort of instances, enabling a deeper understanding of model decisions within a defined context. In this paper, we discuss the unique challenges and opportunities associated with measuring cohort explanations, define their desired properties, and create a generalized framework for generating cohort explanations based on supervised clustering.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

  • Qiying Yu
  • Zheng Zhang
  • Ruofei Zhu
  • Yufeng Yuan
  • Xiaochen Zuo
  • Yu Yue
  • Weinan Dai
  • Tiantian Fan

Inference scaling empowers LLMs with unprecedented reasoning ability, with reinforcement learning as the core technique to elicit complex reasoning. However, key technical details of state-of-the-art reasoning LLMs are concealed (such as in OpenAI o1 blog and DeepSeek R1 technical report), thus the community still struggles to reproduce their RL training results. We propose the D ecoupled Clip and D ynamic s A mpling P olicy O ptimization ( DAPO ) algorithm, and fully open-source a state-of-the-art large-scale RL system that achieves 50 points on AIME 2024 using Qwen2. 5-32B base model. Unlike previous works that withhold training details, we introduce four key techniques of our algorithm that make large-scale LLM RL a success. In addition, we open-source our training code, which is built on the verl framework, along with a carefully curated and processed dataset. These components of our open-source system enhance reproducibility and support future research in large-scale LLM RL.

PDF Details

ICML Conference 2025 Conference Paper

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data

  • Siqi Guo 0003
  • Ilgee Hong
  • Vicente Balmaseda
  • Changlong Yu
  • Liang Qiu
  • Xin Liu
  • Haoming Jiang
  • Tuo Zhao

Supervised fine-tuning (SFT) has become a crucial step for aligning pretrained large language models (LLMs) using supervised datasets of input-output pairs. However, despite being supervised, SFT is inherently limited by its generative training objective. To address its limitations, the existing common strategy is to follow SFT with a separate phase of preference optimization (PO), which relies on either human-labeled preference data or a strong reward model to guide the learning process. In this paper, we address the limitations of SFT by exploring one of the most successful techniques in conventional supervised learning: discriminative learning. We introduce Discriminative Fine-Tuning (DFT), an improved variant of SFT, which mitigates the burden of collecting human-labeled preference data or training strong reward models. Unlike SFT that employs a generative approach and overlooks negative data, DFT adopts a discriminative paradigm that increases the probability of positive answers while suppressing potentially negative ones, aiming for data prediction instead of token prediction. Our contributions include: (i) a discriminative probabilistic framework for fine-tuning LLMs by explicitly modeling the discriminative likelihood of an answer among all possible outputs given an input; (ii) efficient algorithms to optimize this discriminative likelihood; and (iii) extensive experiments demonstrating DFT’s effectiveness, achieving performance better than SFT and comparable to if not better than SFT$\rightarrow$PO. The code can be found at https: //github. com/Optimization-AI/DFT.

Details

JBHI Journal 2025 Journal Article

DTI-MvSCA: An Anti-Over-Smoothing Multi-View Framework With Negative Sample Selection for Predicting Drug-Target Interactions

  • Lihong Peng
  • Zongzheng Bai
  • Longlong Liu
  • Long Yang
  • Xin Liu
  • Min Chen
  • Xing Chen

Predicting potential drug-target interactions (DTIs) facilitates to accelerate drug discovery and reduce development cost. Current deep learning-based methods exhibit high-performance predictions, but three challenges remain: first, the absence of negative DTIs severely limits the model performance. Moreover, existing graph neural networks are beset with the scalability due to the model complexity and graph size. More importantly, most methods focus on learning the topological features while ignoring node features during DTI representation learning. To solve the limitations, here, we develop a multi-view neural network framework called DTI-MvSCA for DTI identification. This framework begins with constructing a drug-protein pair (DPP) network with matrix operation-based negative DTI selection, and then learns the DPP representations through a M ulti- v iew neural network, finally classifies each DPP based on multilayer perceptron. Particularly, the multi-view neural network integrates graph topological feature learning based on the self-attention mechanism and S HADOW graph attention network, node feature learning based on 1D C onvolutional neural network, and the A ttention mechanism. An in-depth experiment on DrugBank V3. 0 and V5. 0 showed that DTI-MvSCA obtained precise and robust predictions against five state-of-the-art baseline methods. Furthermore, visualizing the feature distributions of the selected negative DTIs exhibits a more distinguishable and clearer boundary. In summary, DTI-MvSCA provides a useful deep learning tool to investigate potential DTIs.

Details DOI

NeurIPS Conference 2025 Conference Paper

DUO: No Compromise to Accuracy Degradation

  • Jinda Jia
  • Cong Xie
  • Hanlin Lu
  • Fanjiang Ye
  • Hao Feng
  • Daoce Wang
  • Haibin Lin
  • Zhi Zhang

Distributed training often suffers from high communication overhead due to large-scale gradient synchronization. Although gradient compression—particularly at 4-bit or even lower precision—significantly reduces transfer volume, it typically results in sacrifice in precision and degradation of the final model accuracy. In this work, we introduce DUO, a distributed training framework designed to mitigate accuracy degradation incurred by gradient compression without involving additional overhead. DUO achieves this by inserting an additional high-precision gradient synchronization step into a previously computation-only phase, so that its communication is fully hidden by computation. We provide a comprehensive theoretical proof of convergence for DUO and validate its effectiveness through extensive pre-training experiments on GPT models. Our results indicate that DUO effectively restores accuracy when using 4-bit gradient compression, achieving performance comparable to uncompressed training. Remarkably, DUO maintains minimal accuracy degradation even under extreme compression scenarios, including 1-bit gradients or complete omission of the low-precision gradient communication step (0-bit transmission).

PDF Details

IJCAI Conference 2025 Conference Paper

DUQ: Dual Uncertainty Quantification for Text-Video Retrieval

  • Xin Liu
  • Shibai Yin
  • Jun Wang
  • Jiaxin Zhu
  • Xingyang Wang
  • Yee-Hong Yang

Text-video retrieval establishes accurate similarity relationships between text and video through feature enhancement and granularity alignment. However, relying solely on similarity to associate intra-pair features and distinguish inter-pair features is insufficient, \textit{e. g. }, when querying a multi-scene video with sparse text or selecting the most relevant video from many similar candidates. In this paper, we propose a novel Dual Uncertainty Quantification (DUQ) model that separately handles uncertainties in intra-pair interaction and inter-pair exclusion. Specifically, to enhance intra-pair interaction, we propose an intra-pair similarity uncertainty module to provide similarity-based trustworthy predictions and explicitly model this uncertainty. To increase inter-pair exclusion, we propose an inter-pair distance uncertainty module to construct a distance-based diversity probability embeding, thereby widening the gap between similar features. The two components work synergistically, jointly improving the calculation of similarity between features. We evaluate our model on six benchmark datasets: MSRVTT (51. 2%), DiDeMo, MSVD, LSMDC, Charades, and VATEX, achieving state-of-the-art retrieval performance.

PDF Details DOI

EAAI Journal 2025 Journal Article

Enhanced multi-modal emotion recognition using the feature level fusion

  • Aziguli Wulamu
  • Yuheng Wu
  • Xin Liu
  • Yao Zhang
  • Jinghan Xu
  • Yang Zhang

Multi-modal human emotion recognition is a complex process of synthesizing information from various modalities to calculate emotion states. This field faces several challenges: (1) Acoustic is an essential component of emotion expression, but it often underperforms compared to visual and text in emotion recognition. (2) Capturing the feature interaction among different modalities is usually complex. (3) Processing high-definition videos can significantly reduce the efficiency of visual analysis. In this study, we presented a learning architecture designed to recognize human emotions effectively. For the first challenge, we implemented a multi-level acoustic encoder (MLAE) that enhances the extraction of acoustic information to improve the acoustic contribution in multi-modal emotion recognition. Facing the second challenge, we introduced the cross-attention block module, which adeptly captures the inter-modal interactions. To address the third challenge, we adopted the re-parameterized visual geometry group network (RepVGG) as the visual feature encoder, employing its multi-branch learning and single-branch reasoning structure to maintain high reasoning efficiency. Our model has demonstrated the state-of-the-art performance of the interactive emotional dyadic motion capture (IEMOCAP) dataset and the multi-modal opinion sentiment and emotion intensity of the Carnegie Mellon University (CMU-MOSEI) dataset.

Details DOI

NeurIPS Conference 2025 Conference Paper

Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

  • Xiyue Peng
  • Hengquan Guo
  • Jiawei Zhang
  • Dongqing Zou
  • Ziyu Shao
  • Honghao Wei
  • Xin Liu

Balancing helpfulness and safety (harmlessness) is a critical challenge in aligning large language models (LLMs). Current approaches often decouple these two objectives, training separate preference models for helpfulness and safety, while framing safety as a constraint within a constrained Markov Decision Process (CMDP) framework. This paper identifies a potential issue when using the widely adopted expected safety constraints for LLM safety alignment, termed "safety compensation'', where the constraints are satisfied on expectation, but individual prompts may trade off safety, resulting in some responses being overly restrictive while others remain unsafe. To address this issue, we propose Rectified Policy Optimization (RePO), which replaces the expected safety constraint with critical safety constraints imposed on every prompt. At the core of RePO is a policy update mechanism driven by rectified policy gradients, which penalizes the strict safety violation of every prompt, thereby enhancing safety across nearly all prompts. Our experiments demonstrate that RePO outperforms strong baseline methods and significantly enhances LLM safety alignment.

PDF Details

AAAI Conference 2025 Conference Paper

Exploring the Better Multimodal Synergy Strategy for Vision-Language Models

  • Xiaotian Yin
  • Xin Liu
  • Si Chen
  • Yuan Wang
  • Yuwen Pan
  • Tianzhu Zhang

Vision-Language models (VLMs) have shown great potential in enhancing open-world visual concept comprehension. Recent researches focus on an optimum multimodal collaboration strategy that significantly advances CLIP-based few-shot tasks. However, existing prompt-based solutions suffer from unidirectional information flow and increased parameters since they explicitly condition the vision prompts on textual prompts across different transformer layers using non-shareable coupling functions. To address this issue, we propose a Dual-shared mechanism based on LoRA (DsRA) that addresses VLM adaptation in low-data regimes. The proposed DsRA enjoys several merits. First, we design an inter-modal shared coefficient that focuses on capturing visual and textual shared patterns, ensuring effective mutual synergy between image and text features. Second, an intra-modal shared matrix is proposed to achieve efficient parameter fine-tuning by combining the different coefficients to generate layer-wise adapters placed in encoder layers. Our extensive experiments demonstrate that DsRA improves the generalizability under few-shot classification, base-to-new generalization, and domain generalization settings. Our code will be released soon.

PDF Details DOI

ECAI Conference 2025 Conference Paper

Latent Knowledge Scalpel: Precise and Massive Knowledge Editing for Large Language Models

  • Xin Liu
  • Qiyang Song
  • Shaowen Xu
  • Kerou Zhou
  • Wenbo Jiang
  • Xiaoqi Jia
  • Weijuan Zhang
  • Heqing Huang 0001

Large Language Models (LLMs) often retain inaccurate or outdated information from pre-training, leading to incorrect predictions or biased outputs during inference. While existing model editing methods can address this challenge, they struggle with editing large amounts of factual information simultaneously and may compromise the general capabilities of the models. In this paper, our empirical study demonstrates that it is feasible to edit the internal representations of LLMs and replace the entities in a manner similar to editing natural language inputs. Based on this insight, we introduce the Latent Knowledge Scalpel (LKS), an LLM editor that manipulates the latent knowledge of specific entities via a lightweight hypernetwork to enable precise and large-scale editing. Experiments conducted on Llama-2 and Mistral show even with the number of simultaneous edits reaching 10, 000, LKS effectively performs knowledge editing while preserving the general abilities of the edited LLMs. Code is available at: https: //github. com/Linuxin-xxx/LKS.

Details

NeurIPS Conference 2025 Conference Paper

Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning

  • Ziqi Gu
  • Chunyan Xu
  • Wenxuan Fang
  • Xin Liu
  • Yide Qiu
  • Zhen Cui

Multi-domain task incremental learning (MTIL) demands models to master domain-specific expertise while preserving generalization capabilities. Inspired by human lifelong learning, which relies on revisiting, aligning, and integrating past experiences, we propose a Learning and Ensembling Bridge Adapters (LEBA) framework. To facilitate cohesive knowledge transfer across domains, specifically, we propose a continuous-domain bridge adaptation module, leveraging the distribution transfer capabilities of Schrödinger bridge for stable progressive learning. To strengthen memory consolidation, we further propose a progressive knowledge ensemble strategy that revisits past task representations via a diffusion model and dynamically integrates historical adapters. For efficiency, LEBA maintains a compact adapter pool through similarity-based selection and employs learnable weights to align replayed samples with current task semantics. Together, these components effectively mitigate catastrophic forgetting and enhance generalization across tasks. Extensive experiments across multiple benchmarks validate the effectiveness and superiority of LEBA over state-of-the-art methods.

PDF Details

ICLR Conference 2025 Conference Paper

Minimax Optimal Two-Stage Algorithm For Moment Estimation Under Covariate Shift

  • Zhen Zhang
  • Xin Liu
  • Shaoli Wang
  • Jiaye Teng

Covariate shift occurs when the distribution of input features differs between the training and testing phases. In covariate shift, estimating an unknown function's moment is a classical problem that remains under-explored, despite its common occurrence in real-world scenarios. In this paper, we investigate the minimax lower bound of the problem when the source and target distributions are known. To achieve the minimax optimal bound (up to a logarithmic factor), we propose a two-stage algorithm. Specifically, it first trains an optimal estimator for the function under the source distribution, and then uses a likelihood ratio reweighting procedure to calibrate the moment estimator. In practice, the source and target distributions are typically unknown, and estimating the likelihood ratio may be unstable. To solve this problem, we propose a truncated version of the estimator that ensures double robustness and provide the corresponding upper bound. Extensive numerical studies on synthetic examples confirm our theoretical findings and further illustrate the effectiveness of our proposed method.

Details

JBHI Journal 2025 Journal Article

Multi-Omics Graph Knowledge Representation for Pneumonia Prognostic Prediction

  • Wenyu Xing
  • Miao Li
  • Yiwen Liu
  • Xin Liu
  • Yifang Li
  • Yanping Yang
  • Jing Bi
  • Jiangang Chen

Early prognostic prediction is crucial for determining appropriate clinical interventions. Previous single-omics models had limitations, such as high contingency and overlooking complex physical conditions. In this paper, we introduced multi-omics graph knowledge representation to predict in-hospital outcomes for pneumonia patients. This method utilizes CT imaging and three non-imaging omics information, and explores a knowledge graph for modeling multi-omics relations to enhance the overall information representation. For imaging omics, a multichannel pyramidal recursive MLP and Longformer-based 3D deep learning module was developed to extract depth features in lung window, while radiomics features were simultaneously extracted in both lung and mediastinal windows. Non-imaging omics involved the adoption of laboratory, microbial, and clinical indices to complement the patient's physical condition. Following feature screening, the similarity fusion network and graph convolutional network (GCN) were employed to determine omics similarity and provide prognostic prediction. The results of comparative experiments and generalization validation demonstrat that the proposed multi-omics GCN-based prediction model has good robustness and outperformed previous single-type omics, classical machine learning, and previous deep learning methods. Thus, the proposed multi-omics graph knowledge representation model enhances early prognostic prediction performance in pneumonia, facilitating a comprehensive assessment of disease severity and timely intervention for high-risk patients.

Details DOI

IJCAI Conference 2025 Conference Paper

No Regret Reinforcement Learning Algorithms for Online Scheduling with Multi-Stage Tasks

  • Yongxin Xu
  • Hengquan Guo
  • Ziyu Shao
  • Xin Liu

We study online task scheduling problems where tasks arrive sequentially and are processed by the platform or server. The service processes for tasks are multi-stage and are modeled as episodic Markov Decision Processes (MDPs). While processing a task, the system acquires rewards by consuming resources. The goal of the platform is to maximize the reward-to-cost ratio over a sequence of K tasks. Online scheduling with multi-stage tasks faces two major challenges: intra-dependence among the different stages within a task and inter-dependence among different tasks. These challenges are further exacerbated by the unknown rewards, costs, and task arrival distribution. To address these challenges, we propose the Robbins-Monro-based Value Iteration for Ratio Maximization (RM^2VI) algorithm. Specifically, RM^2VI addresses ``intra-dependence'' through optimistic value iteration and handles ``inter-dependence'' using the Robbins-Monro method. The algorithm has a greedy structure and achieves a sub-linear regret of O(K^(3/4)), establishing the no-regret property (per-task). We test RM^2VI in two synthetic experiments of sale promotion in E-commerce and machine learning job training in cloud computing. The results show RM^2VI achieves the best reward-to-cost ratio compared with the baselines.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

On the Power of Optimism in Constrained Online Convex Optimization

  • Haobo Zhang
  • Hengquan Guo
  • Xin Liu

This paper studies the constrained online convex optimization problem (COCO) where the learner makes sequential decisions within a constrained set. We present Optimistic-COCO, an adaptive gradient-based algorithm that incorporates optimistic design with the Lyapunov optimization technique. The proposed algorithm achieves strong theoretical guarantees: 1) Optimistic-COCO provides a tight gradient-variation regret bound and constant constraint violation; 2) Optimistic-COCO is environment-agnostic, utilizing adaptive learning rates that rely solely on causal information. These results resolve an open question posed in prior work regarding whether an adaptive algorithm can achieve problem-dependent regret and constant constraint violation in COCO. We establish these robust guarantees through carefully designed adaptive parameters and a refined multi-step Lyapunov drift analysis. Experimental results further validate our theoretical findings, demonstrating the practical efficacy of the proposed algorithm.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

RADAR: Benchmarking Language Models on Imperfect Tabular Data

  • Ken Gu
  • Zhihan Zhang
  • Kate Lin
  • Yuwei Zhang
  • Akshay Paruchuri
  • Hong Yu
  • Mehran Kazemi
  • Kumar Ayush

Language models (LMs) are increasingly being deployed to perform autonomous data analyses. However, their data awareness—the ability to recognize, reason over, and appropriately handle data artifacts such as missing values, outliers, and logical inconsistencies—remains underexplored. These artifacts are especially common in real-world tabular data and, if mishandled, can significantly compromise the validity of analytical conclusions. To address this gap, we present RADAR, a benchmark for systematically evaluating data-aware reasoning on tabular data. We develop a framework to simulate data artifacts via programmatic perturbations to enable targeted evaluation of model behavior. RADAR comprises 2, 980 table-query pairs, grounded in real-world data spanning 9 domains and 5 data artifact types. In addition to evaluating artifact handling, RADAR systematically varies table size to study how reasoning performance holds when increasing table size. Our evaluation reveals that, despite decent performance on tables without data artifacts, frontier models degrade significantly when data artifacts are introduced, exposing critical gaps in their capacity for robust, data-aware analysis. Designed to be flexible and extensible, RADAR supports diverse perturbation types and controllable table sizes, offering a valuable resource for advancing tabular reasoning.

PDF Details

AAAI Conference 2025 Conference Paper

Re-Attentional Controllable Video Diffusion Editing

  • Yuanzhi Wang
  • Yong Li
  • Mengyi Liu
  • Xiaoya Zhang
  • Xin Liu
  • Zhen Cui
  • Antoni B. Chan

Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by proposing a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method. Specially, to align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD) to refocus the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video. In particular, to faithfully preserve the invariant region content with less border artifacts, we propose an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors w.r.t the invariant regions at each denoising timestep and constrain the generated content to be harmonized with the invariant region content. Experimental results verify that ReAtCo consistently improves the controllability of video diffusion editing and achieves superior video editing performance.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Scene Graph-Grounded Image Generation

  • Fuyun Wang
  • Tong Zhang
  • Yuanzhi Wang
  • Xiaoya Zhang
  • Xin Liu
  • Zhen Cui

With the beneft of explicit object-oriented reasoning capabilities of scene graphs, scene graph-to-image generation has made remarkable advancements in comprehending object coherence and interactive relations. Recent state-of-the-arts typically predict the scene layouts as an intermediate representation of a scene graph before synthesizing the image. Nevertheless, transforming a scene graph into an exact layout may restrict its representation capabilities, leading to discrepancies in interactive relationships (such as standing on, wearing, or covering) between the generated image and the input scene graph. In this paper, we propose a Scene Graph-Grounded Image Generation (SGG-IG) method to mitigate the above issues. Specifcally, to enhance the scene graph representation, we design a masked auto-encoder module and a relation embedding learning module to integrate structural knowledge and contextual information of the scene graph with a mask self-supervised manner. Subsequently, to bridge the scene graph with visual content, we introduce a spatial constraint and image-scene alignment constraint to capture the fne-grained visual correlation between the scene graph symbol representation and the corresponding image representation, thereby generating semantically consistent and high-quality images. Extensive experiments demonstrate the effectiveness of the method both quantitatively and qualitatively.

PDF Details DOI

EAAI Journal 2025 Journal Article

Seafloor topography inversion from multi-source marine gravity data using multi-channel convolutional neural network

  • Bangzhuang Ge
  • Jinyun Guo
  • Qiaoli Kong
  • Chengcheng Zhu
  • Lingyong Huang
  • Heping Sun
  • Xin Liu

Seafloor topography is extremely important for marine scientific surveys and research. Current physical methods have difficulties in integrating multi-source marine gravity data and recovering non-linear features. To overcome this challenge, a multi-channel convolutional neural network (MCCNN) is employed to establish the seafloor topography model. Firstly, the MCCNN model is trained using the input data from the 64 × 64 grid points centered around the control points. The input data includes the differences in position between calculation points and surrounding grid points, gravity anomaly, vertical gravity gradient, east component of deflection of the vertical and north component of deflection of the vertical, as well as the reference terrain information. Then, the data from the 64 × 64 grid points centered around the predicted points is inputted into the trained MCCNN model to obtain the predicted depth at those points. Finally, the predicted depth is utilized to establish the seafloor topography model of the study area. This method is tested in a local area located in the southern part of the Emperor Seamount Chain in the Northwest Pacific (31°N −37°N, 169°E −175°E). The root mean square of the differences between the resultant seafloor topography model and ship-borne bathymetric values at the check points is 88. 48 m. This performance is commendable compared to existing models.

Details DOI

NeurIPS Conference 2025 Conference Paper

SensorLM: Learning the Language of Wearable Sensors

  • Yuwei Zhang
  • Kumar Ayush
  • Siyuan Qiao
  • A. Ali Heydari
  • Girish Narayanswamy
  • Max Xu
  • Ahmed Metwally
  • Jinhua Xu

We present SensorLM, a family of sensor-language foundation models that enable wearable sensor data understanding with natural language. Despite its pervasive nature, aligning and interpreting sensor data with language remains challenging due to the lack of paired, richly annotated sensor-text descriptions in uncurated, real-world wearable data. We introduce a hierarchical caption generation pipeline designed to capture statistical, structural, and semantic information from sensor data. This approach enabled the curation of the largest sensor-language dataset to date, comprising over 59. 7 million hours of data from more than 103, 000 people. Furthermore, SensorLM extends prominent multimodal pretraining architectures (e. g. , CLIP, CoCa) and recovers them as specific variants within a generic architecture. Extensive experiments on real-world tasks in human activity analysis and healthcare verify the superior performance of SensorLM over state-of-the-art in zero-shot recognition, few-shot learning, and cross-modal retrieval. SensorLM also demonstrates intriguing capabilities including scaling behaviors, label efficiency, sensor captioning, and zero-shot generalization to unseen tasks. Code is available at https: //github. com/Google-Health/consumer-health-research/tree/main/sensorlm.

PDF Details

NeurIPS Conference 2025 Conference Paper

SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback

  • Bo Lv
  • Nayu Liu
  • Chen Tang
  • Xin Liu
  • Yue Yu
  • Ping Luo

Ensembles of generative large language models (LLMs) are a promising way to compensate for individual model limitations, integrating the strengths of different LLMs. Existing LLM ensemble methods, however, face limitations such as first-token delay and challenges in long-range semantic collaboration between models, Moreover, they typically assume equal voting weights for all models during ensemble, ignoring performance differences between models for a given task. In this work, we propose SpecEM, a training-free, plug-and-play LLM ensemble framework that dynamically adjusts each model's model contribution in real time based on task performance. Inspired by speculative decoding, SpecFuse iteratively performs drafting and verification, allowing models to collaborate semantically at the segment level for integrated output. Furthermore, we introduce an online feedback mechanism with multiplicative weight updates, where each model's voting weight is adjusted on-the-fly according to how often it "outperforms" others during verification stage, ensuring that stronger models exert greater influence on the ensemble during generation. Experimental results on five popular LLMs (ranging from 7B to 72B parameters) and six benchmark tasks, spanning instruction following, reasoning, commonsense, and general instruction response, demonstrate consistent performance improvements compared to state-of-the-art LLM ensemble methods.

PDF Details

NeurIPS Conference 2025 Conference Paper

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models

  • Ilgee Hong
  • Changlong Yu
  • Liang Qiu
  • Weixiang Yan
  • Zhenghao Xu
  • Haoming Jiang
  • Qingru Zhang
  • Qin Lu

Reinforcement learning from human feedback (RLHF) has become a powerful post-training paradigm for aligning large language models with human preferences. A core challenge in RLHF is constructing accurate reward signals, where the conventional Bradley-Terry reward models (BT RMs) often suffer from sensitivity to data size and coverage, as well as vulnerability to reward hacking. Generative reward models (GenRMs) offer a more robust alternative by generating chain-of-thought (CoT) rationales followed by a final verdict. However, existing GenRMs rely on shallow, vertically scaled reasoning, limiting their capacity to handle nuanced or complex tasks. Moreover, their pairwise preference outputs are incompatible with standard RLHF algorithms that require pointwise reward signals. In this work, we introduce Think-RM, a training framework that enables long-horizon reasoning in GenRMs by modeling an internal thinking process. Rather than producing structured, externally provided rationales, Think-RM generates flexible, self-guided reasoning traces that support advanced capabilities such as self-reflection, hypothetical reasoning, and divergent reasoning. To elicit these reasoning abilities, we first warm-up the models by supervised fine-tuning (SFT) over long CoT data. We then further improve the model's long-horizon abilities by rule-based reinforcement learning (RL). In addition, we propose a novel pairwise RLHF pipeline that directly optimizes policies from pairwise comparisons, eliminating the need for pointwise reward conversion. Experiments show that Think-RM outperforms baselines on both in-distribution and out-of-distribution tasks, with particularly strong gains on reasoning-heavy benchmarks: more than 10\% and 5\% on RewardBench's Chat Hard and Reasoning, and 12\% on RM-Bench's Math domain. When combined with our pairwise RLHF pipeline, it demonstrates superior end-policy performance compared to traditional approaches. This depth-oriented approach not only broadens the GenRM design space but also establishes a new paradigm for preference-based policy optimization in RLHF.

PDF Details

ICML Conference 2025 Conference Paper

Triple-Optimistic Learning for Stochastic Contextual Bandits with General Constraints

  • Hengquan Guo
  • Lingkai Zu
  • Xin Liu

We study contextual bandits with general constraints, where a learner observes contexts and aims to maximize cumulative rewards while satisfying a wide range of general constraints. We introduce the Optimistic$^3$ framework, a novel learning and decision-making approach that integrates optimistic design into parameter learning, primal decision, and dual violation adaptation (i. e. , triple-optimism), combined with an efficient primal-dual architecture. Optimistic$^3$ achieves $\tilde{O}(\sqrt{T})$ regret and constraint violation for contextual bandits with general constraints. This framework not only outperforms the state-of-the-art results that achieve $\tilde{O}(T^{\frac{3}{4}})$ guarantees when Slater’s condition does not hold but also improves on previous results that achieve $\tilde{O}(\sqrt{T}/\delta)$ when Slater’s condition holds ($\delta$ denotes the Slater’s condition parameter), offering a $O(1/\delta)$ improvement. Note this improvement is significant because $\delta$ can be arbitrarily small when constraints are particularly challenging. Moreover, we show that Optimistic$^3$ can be extended to classical multi-armed bandits with both stochastic and adversarial constraints, recovering the best-of-both-worlds guarantee established in the state-of-the-art works, but with significantly less computational overhead.

Details

NeurIPS Conference 2025 Conference Paper

Videos are Sample-Efficient Supervisions: Behavior Cloning from Videos via Latent Representations

  • Xin Liu
  • Haoran Li
  • Dongbin Zhao

Humans can efficiently extract knowledge and learn skills from the videos within only a few trials and errors. However, it poses a big challenge to replicate this learning process for autonomous agents, due to the complexity of visual input, the absence of action or reward signals, and the limitations of interaction steps. In this paper, we propose a novel, unsupervised, and sample-efficient framework to achieve imitation learning from videos (ILV), named Behavior Cloning from Videos via Latent Representations (BCV-LR). BCV-LR extracts action-related latent features from high-dimensional video inputs through self-supervised tasks, and then leverages a dynamics-based unsupervised objective to predict latent actions between consecutive frames. The pre-trained latent actions are fine-tuned and efficiently aligned to the real action space online (with collected interactions) for policy behavior cloning. The cloned policy in turn enriches the agent experience for further latent action finetuning, resulting in an iterative policy improvement that is highly sample-efficient. We conduct extensive experiments on a set of challenging visual tasks, including both discrete control and continuous control. BCV-LR enables effective (even expert-level on some tasks) policy performance with only a few interactions, surpassing state-of-the-art ILV baselines and reinforcement learning methods (provided with environmental rewards) in terms of sample efficiency across 24/28 tasks. To the best of our knowledge, this work for the first time demonstrates that videos can support extremely sample-efficient visual policy learning, without the need to access any other expert supervision.

PDF Details

AAAI Conference 2025 Conference Paper

Zero-shot Video Restoration and Enhancement Using Pre-Trained Image Diffusion Model

  • Cong Cao
  • Huanjing Yue
  • Xin Liu
  • Jingyu Yang

Diffusion-based zero-shot image restoration and enhancement models have achieved great success in various tasks of image restoration and enhancement. However, directly applying them to video restoration and enhancement results in severe temporal flickering artifacts. In this paper, we propose the first framework for zero-shot video restoration and enhancement based on the pre-trained image diffusion model. By replacing the spatial self-attention layer with the proposed short-long-range (SLR) temporal attention layer, the pre-trained image diffusion model can take advantage of the temporal correlation between frames. We further propose temporal consistency guidance, spatial-temporal noise sharing, and an early stopping sampling strategy to improve temporally consistent sampling. Our method is a plug-and-play module that can be inserted into any diffusion-based image restoration or enhancement methods to further improve their performance. Experimental results demonstrate the superiority of our proposed method.

PDF Details DOI

JMLR Journal 2024 Journal Article

Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees

  • Nachuan Xiao
  • Xiaoyin Hu
  • Xin Liu
  • Kim-Chuan Toh

In this paper, we present a comprehensive study on the convergence properties of Adam-family methods for nonsmooth optimization, especially in the training of nonsmooth neural networks. We introduce a novel two-timescale framework that adopts a two-timescale updating scheme, and prove its convergence properties under mild assumptions. Our proposed framework encompasses various popular Adam-family methods, providing convergence guarantees for these methods in training nonsmooth neural networks. Furthermore, we develop stochastic subgradient methods that incorporate gradient clipping techniques for training nonsmooth neural networks with heavy-tailed noise. Through our framework, we show that our proposed methods converge even when the evaluation noises are only assumed to be integrable. Extensive numerical experiments demonstrate the high efficiency and robustness of our proposed methods. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

NeurIPS Conference 2024 Conference Paper

Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning

  • Honghao Wei
  • Xiyue Peng
  • Arnob Ghosh
  • Xin Liu

We propose WSAC (Weighted Safe Actor-Critic), a novel algorithm for Safe Offline Reinforcement Learning (RL) under functional approximation, which can robustly optimize policies to improve upon an arbitrary reference policy with limited data coverage. WSAC is designed as a two-player Stackelberg game to optimize a refined objective function. The actor optimizes the policy against two adversarially trained value critics with small importance-weighted Bellman errors, which focus on scenarios where the actor's performance is inferior to the reference policy. In theory, we demonstrate that when the actor employs a no-regret optimization oracle, WSAC achieves a number of guarantees: $(i)$ For the first time in the safe offline RL setting, we establish that WSAC can produce a policy that outperforms {\bf any} reference policy while maintaining the same level of safety, which is critical to designing a safe algorithm for offline RL. $(ii)$ WSAC achieves the optimal statistical convergence rate of $1/\sqrt{N}$ to the reference policy, where $N$ is the size of the offline dataset. $(iii)$ We theoretically show that WSAC guarantees a safe policy improvement across a broad range of hyperparameters that control the degree of pessimism, indicating its practical robustness. Additionally, we offer a practical version of WSAC and compare it with existing state-of-the-art safe offline RL algorithms in several continuous control environments. WSAC outperforms all baselines across a range of tasks, supporting the theoretical results.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Convergence Analysis of Split Federated Learning on Heterogeneous Data

  • Pengchao Han
  • Chao Huang
  • Geng Tian
  • Ming Tang
  • Xin Liu

Split federated learning (SFL) is a recent distributed approach for collaborative model training among multiple clients. In SFL, a global model is typically split into two parts, where clients train one part in a parallel federated manner, and a main server trains the other. Despite the recent research on SFL algorithm development, the convergence analysis of SFL is missing in the literature, and this paper aims to fill this gap. The analysis of SFL can be more challenging than that of federated learning (FL), due to the potential dual-paced updates at the clients and the main server. We provide convergence analysis of SFL for strongly convex and general convex objectives on heterogeneous data. The convergence rates are $O(1/T)$ and $O(1/\sqrt[3]{T})$, respectively, where $T$ denotes the total number of rounds for SFL training. We further extend the analysis to non-convex objectives and where some clients may be unavailable during training. Numerical experiments validate our theoretical results and show that SFL outperforms FL and split learning (SL) when data is highly heterogeneous across a large number of clients.

PDF Details DOI

ECAI Conference 2024 Conference Paper

Coopetition in Heterogeneous Cross-Silo Federated Learning

  • Chao Huang
  • Justin Dachille
  • Xin Liu

In cross-silo federated learning (FL), companies collaboratively train a shared global model without sharing heterogeneous data. Prior related work focused on algorithm development to tackle data heterogeneity. However, the dual problem of coopetition, i. e. , FL collaboration and market competition, remains under-explored. This paper studies the FL coopetition using a dynamic two-period game model. In period 1, an incumbent company trains a local model and provides model-based services at a chosen price to users. In period 2, an entrant company enters, and both companies decide whether to engage in FL collaboration and then compete in selling model-based services at different prices to users. Analyzing the two-period game is challenging due to data heterogeneity, and that the incumbent’s period one pricing has a temporal impact on coopetition in period 2, resulting in a non-concave problem. To address this issue, we decompose the problem into several concave sub-problems and develop an algorithm that achieves a global optimum. Numerical results on three public datasets show two interesting insights. First, FL training brings model performance gain as well as competition loss, and collaboration occurs only when the performance gain outweighs the loss. Second, data heterogeneity can incentivize the incumbent to limit market penetration in period 1 and promote price competition in period 2.

Details

IROS Conference 2024 Conference Paper

Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits

  • Yinghui Li
  • Jinze Wu
  • Xin Liu
  • Weizhong Guo
  • Yufei Xue

Legged robots excel in navigating complex terrains, yet learning natural and robust motions in such environments remains challenging. Inspired by animals’ experience-based stepwise learning process, we propose a two-stage framework for legged robots to progressively learn naturally robust movements using a two-step reward method. Initially robots learn the fundamental gaits on flat terrains with gait-rewards and generating valuable motion data. Subsequently, leveraging learned motion experience, they adopt adversarial imitation learning to tackle challenging terrains with refined movements. Our method addresses the challenge of acquiring effective imitation data and facilitates the learning process under various gait parameters with ease. The effectiveness of this approach has been validated on both quadruped and hexapod robots, demonstrating naturally robust gaits in real-world applications.

Details

JMLR Journal 2024 Journal Article

Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment

  • Zixian Yang
  • Xin Liu
  • Lei Ying

The traditional multi-armed bandit (MAB) model for recommendation systems assumes the user stays in the system for the entire learning horizon. In new online education platforms such as ALEKS or new video recommendation systems such as TikTok, the amount of time a user spends on the app depends on how engaging the recommended contents are. Users may temporarily leave the system if the recommended items cannot engage the users. To understand the exploration, exploitation, and engagement in these systems, we propose a new model, called MAB-A where “A” stands for abandonment and the abandonment probability depends on the current recommended item and the user's past experience (called state). We propose two algorithms, ULCB and KL-ULCB, both of which do more exploration (being optimistic) when the user likes the previous recommended item and less exploration (being pessimistic) when the user does not. We prove that both ULCB and KL-ULCB achieve logarithmic regret, $O(\log K)$, where $K$ is the number of visits (or episodes). Furthermore, the regret bound under KL-ULCB is asymptotically sharp. We also extend the proposed algorithms to the general-state setting. Simulation results show that the proposed algorithms have significantly lower regret than the traditional UCB and KL-UCB, and Q-learning-based algorithms. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

AAMAS Conference 2024 Conference Paper

Learning to Schedule Online Tasks with Bandit Feedback

  • Yongxin Xu
  • Shangshang Wang
  • Hengquan Guo
  • Xin Liu
  • Ziyu Shao

Online task scheduling serves an integral role for task-intensive applications in cloud computing and crowdsourcing. Optimal scheduling can enhance system performance, typically measured by the reward-to-cost ratio, under some task arrival distribution. On one hand, both reward and cost are dependent on task context (e. g. , evaluation metric) and remain black-box in practice. These render reward and cost hard to model thus unknown before decision making. On the other hand, task arrival behaviors remain sensitive to factors like unpredictable system fluctuation whereby a prior estimation or the conventional assumption of arrival distribution (e. g. , Poisson) may fail. This implies another practical yet often neglected challenge, i. e. , uncertain task arrival distribution. Towards effective scheduling under a stationary environment with various uncertainties, we propose a double-optimistic learning based Robbins-Monro (DOL-RM) algorithm. Specifically, DOL-RM integrates a learning module that incorporates optimistic estimation for reward-to-cost ratio and a decision module that utilizes the Robbins-Monro method to implicitly learn task arrival distribution while making scheduling decisions. Theoretically, DOL-RM achieves a sub-linear regret of 𝑂(𝑇3/4), which is the first result for online task scheduling under uncertain task arrival distribution and unknown reward and cost. Our numerical results in a synthetic experiment and a real-world application demonstrate the effectiveness of DOL-RM in achieving the best cumulative reward-to-cost ratio compared with other state-of-the-art baselines.

PDF

ICLR Conference 2024 Conference Paper

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

  • Xin Liu
  • Muhammad Khalifa
  • Lu Wang 0008

A model is considered well-calibrated when its probability estimate aligns with the actual likelihood of the output being correct. Calibrating language models (LMs) is crucial, as it plays a vital role in detecting and mitigating hallucinations of LMs as well as building more trustworthy models. However, standard calibration techniques may not be suited for LM calibration. For instance, post-processing methods such as temperature scaling do not reorder the candidate generations. On the other hand, training-based methods require fine-tuning the entire model, which is impractical for LMs of large scale. We present LitCab, a lightweight calibration mechanism consisting of a single linear layer that takes the input text representation and predicts a bias term, which is then added to the LM output logits. LitCab improves model calibration by only adding < 2% of the original model parameters. For evaluation, we construct CaT, a benchmark consisting of eight text generation tasks, covering responses ranging from short phrases to paragraphs. We test LitCab with Llama2-7B, where it improves calibration across all tasks, reducing the average ECE score by as large as 30%. We further conduct a comprehensive evaluation with multiple popular open-sourced LMs from GPT and LLaMA families, yielding the following key findings: (i) Larger models within the same family exhibit better calibration on tasks with short generation tasks, but not necessarily for longer ones. (ii) GPT-family models show superior calibration compared to LLaMA, Llama2, and Vicuna models, despite having much fewer parameters. (iii) Fine-tuning pretrained model (e.g., LLaMA) with samples of limited purpose (e.g., conversations) may lead to worse calibration, highlighting the importance of fine-tuning setups for calibrating LMs.

Details

EAAI Journal 2024 Journal Article

Microgrid control under uncertainty

  • Avishai Halev
  • Yongshuai Liu
  • Xin Liu

Microgrids – decentralized electrical grids that can function both in conjunction with wide area macrogrids and without – are a powerful tool to address energy resiliency and climate change mitigation. Microgrid control, however, remains a challenge; their bespoke nature and the existence of multiple sources of uncertainty lead to a control problem that traditional grid modeling and control techniques are ill-suited to handle. We build a microgrid interface to simulate microgrids under uncertainty and devise off-policy reinforcement learning algorithms to control microgrids. Our algorithms, which incorporate domain randomization and random network distillation for exploration and computational efficiency, achieve performance better than model predictive control and rule based control benchmarks under battery model uncertainty on seven of ten tested scenarios. Our model code is available at https: //github. com/ahalev/Microgrid-Control-Under-Uncertainty and our microgrid simulator is available at https: //github. com/ahalev/python-microgrid.

Details DOI

ICLR Conference 2024 Conference Paper

Predicting Emergent Abilities with Infinite Resolution Evaluation

  • Shengding Hu
  • Xin Liu
  • Xu Han 0007
  • Xinrong Zhang
  • Chaoqun He
  • Weilin Zhao
  • Yankai Lin 0001
  • Ning Ding 0002

The scientific scale-up of large language models (LLMs) necessitates a comprehensive understanding of their scaling properties. However, the existing literature on the scaling properties only yields an incomplete answer: optimization loss decreases predictably as the model size increases, in line with established scaling law; yet no scaling law for task has been established and the task performances are far from predictable during scaling. Task performances typically show minor gains on small models until they improve dramatically once models exceed a size threshold, exemplifying the ''emergent abilities''. In this study, we discover that small models, although they exhibit minor performance, demonstrate critical and consistent task performance improvements that are not captured by conventional evaluation strategies due to insufficient measurement resolution. To measure such improvements, we introduce PassUntil, an evaluation strategy with theoretically infinite resolution, through massive sampling in the decoding phase. With PassUntil, we conduct a quantitative investigation into the scaling law of task performance. The investigation contains two parts. Firstly, a strict task scaling law that is not conventionally known to exist, is identified, enhancing the predictability of task performances. Remarkably, we are able to predict the performance of the 2.4B model on code generation with merely 0.05\% deviation before training starts, which is the first systematic attempt to verify predictable scaling proposed by GPT-4's report. Secondly, underpinned by PassUntil, we are able to study emergent abilities quantitatively. We identify a kind of accelerated emergence whose scaling curve cannot be fitted by standard scaling law function and has a increasing speed. We then examine two hypothesis and imply that the ``multiple circuits hypothesis'' might be responsible for the accelerated emergence.

Details

IJCAI Conference 2024 Conference Paper

Provable Acceleration of Nesterov’s Accelerated Gradient Method over Heavy Ball Method in Training Over-Parameterized Neural Networks

  • Xin Liu
  • Wei Tao
  • Wei Li
  • Dazhi Zhan
  • Jun Wang
  • Zhisong Pan

Due to its simplicity and efficiency, the first-order gradient method has been extensively employed in training neural networks. Although the optimization problem of the neural network is non-convex, recent research has proved that the first-order method is capable of attaining a global minimum during training over-parameterized neural networks, where the number of parameters is significantly larger than that of training instances. Momentum methods, including the heavy ball (HB) method and Nesterov's accelerated gradient (NAG) method, are the workhorse of first-order gradient methods owning to their accelerated convergence. In practice, NAG often exhibits superior performance than HB. However, current theoretical works fail to distinguish their convergence difference in training neural networks. To fill this gap, we consider the training problem of the two-layer ReLU neural network under over-parameterization and random initialization. Leveraging high-resolution dynamical systems and neural tangent kernel (NTK) theory, our result not only establishes tighter upper bounds of the convergence rate for both HB and NAG, but also provides the first theoretical guarantee for the acceleration of NAG over HB in training neural networks. Finally, we validate our theoretical results on three benchmark datasets.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage

  • Haobo Zhang
  • Xiyue Peng
  • Honghao Wei
  • Xin Liu

Offline safe reinforcement learning (RL) aims to find an optimal policy using a pre-collected dataset when data collection is impractical or risky. We propose a novel linear programming (LP) based primal-dual algorithm for convex MDPs that incorporates ``uncertainty'' parameters to improve data efficiency while requiring only partial data coverage assumption. Our theoretical results achieve a sample complexity of $\mathcal{O}(1/(1-\gamma)\sqrt{n})$ under general function approximation, improving the current state-of-the-art by a factor of $1/(1-\gamma)$, where $n$ is the number of data samples in an offline dataset, and $\gamma$ is the discount factor. The numerical experiments validate our theoretical findings, demonstrating the practical efficacy of our approach in achieving improved safety and learning efficiency in safe offline settings.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration

  • Honghao Wei
  • Xin Liu
  • Lei Ying

This paper studies safe Reinforcement Learning (safe RL) with linear function approximation and under hard instantaneous constraints where unsafe actions must be avoided at each step. Existing studies have considered safe RL with hard instantaneous constraints, but their approaches rely on several key assumptions: (i) the RL agent knows a safe action set for every state or knows a safe graph in which all the state-action-state triples are safe, and (ii) the constraint/cost functions are linear. In this paper, we consider safe RL with instantaneous hard constraints without assumption (i) and generalize (ii) to Reproducing Kernel Hilbert Space (RKHS). Our proposed algorithm, LSVI-AE, achieves O(√{d³H⁴K}) regret and O(H √{dK}) hard constraint violation when the cost function is linear and O(H?ₖ √{K}) hard constraint violation when the cost function belongs to RKHS. Here K is the learning horizon, H is the length of each episode, and?ₖ is the information gain w.r.t the kernel used to approximate cost functions. Our results achieve the optimal dependency on the learning horizon K, matching the lower bound we provide in this paper and demonstrating the efficiency of LSVI-AE. Notably, the design of our approach encourages aggressive policy exploration, providing a unique perspective on safe RL with general cost functions and no prior knowledge of safe actions, which may be of independent interest.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Safeguarding Fraud Detection from Attacks: A Robust Graph Learning Approach

  • Jiasheng Wu
  • Xin Liu
  • Dawei Cheng
  • Yi Ouyang
  • Xian Wu
  • Yefeng Zheng

Financial fraud is one of the most significant social issues and has caused tremendous property losses. Graph neural networks (GNNs) have been applied to anti-fraud practices and achieved decent results. However, recent researches have discovered flaws in the robustness of fraud-detection models based on GNNs, enabling fraudsters to mislead them through attacks like data poisoning. In addition, most existing attack-defense models tend to study on ideal settings and lose information during truncation or filtering, which lowers their performances in complicated financial fraud cases. Therefore, in this paper, we propose a novel robust anti-fraud GNN model. In particular, we first design an attack algorithm tampering with both features and structures of graph data to simulate fraudsters' attacking behaviors in real-life complex fraud scenarios. Then we apply singular value decomposition to the graph and learn the decomposed matrices in a GNN model with specifically designed joint losses. This enables our model to learn the graph patterns in low-rank subspaces without losing too much detailed information and fit the graph structure to characteristics including class-homophily and sparsity to guarantee robustness. The proposed approach is experimented on real-world fraud datasets, which demonstrates its advantages in fraud detection and robustness compared with the state-of-the-art baselines.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Safety of Multimodal Large Language Models on Images and Text

  • Xin Liu
  • Yichen Zhu
  • Yunshi Lan
  • Chao Yang
  • Yu Qiao

Attracted by the impressive power of Multimodal Large Language Models (MLLMs), the public is increasingly utilizing them to improve the efficiency of daily work. Nonetheless, the vulnerabilities of MLLMs to unsafe instructions bring huge safety risks when these models are deployed in real-world scenarios. In this paper, we systematically survey current efforts on the evaluation, attack, and defense of MLLMs' safety on images and text. We begin with introducing the overview of MLLMs on images and text and understanding of safety, which helps researchers know the detailed scope of our survey. Then, we review the evaluation datasets and metrics for measuring the safety of MLLMs. Next, we comprehensively present attack and defense techniques related to MLLMs' safety. Finally, we analyze several unsolved issues and discuss promising research directions. The relevant papers are collected at "https: //github. com/isXinLiu/Awesome-MLLM-Safety".

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training

  • Jinda Jia
  • Cong Xie
  • Hanlin Lu
  • Daoce Wang
  • Hao Feng
  • Chengming Zhang
  • Baixi Sun
  • Haibin Lin

Recent years have witnessed a clear trend towards language models with an ever-increasing number of parameters, as well as the growing training overhead and memory usage. Distributed training, particularly through Sharded Data Parallelism (ShardedDP) which partitions optimizer states among workers, has emerged as a crucial technique to mitigate training time and memory usage. Yet, a major challenge in the scalability of ShardedDP is the intensive communication of weights and gradients. While compression techniques can alleviate this issue, they often result in worse accuracy. Driven by this limitation, we propose SDP4Bit (Toward 4Bit Communication Quantization in Sharded Data Parallelism for LLM Training), which effectively reduces the communication of weights and gradients to nearly 4 bits via two novel techniques: quantization on weight differences, and two-level gradient smooth quantization. Furthermore, SDP4Bit presents an algorithm-system co-design with runtime optimization to minimize the computation overhead of compression. Additional to the theoretical guarantees of convergence, we empirically evaluate the accuracy of SDP4Bit on the pre-training of GPT models with up to 6. 7 billion parameters, and the results demonstrate a negligible impact on training loss. Furthermore, speed experiments show that SDP4Bit achieves up to 4. 08× speedup in end-to-end throughput on a scale of 128 GPUs.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Models

  • Yilun Jin
  • Zheng Li
  • Chenwei Zhang
  • Tianyu Cao
  • Yifan Gao
  • Pratik Jayarao
  • Mao Li
  • Xin Liu

Online shopping is a complex multi-task, few-shot learning problem with a wide and evolving range of entities, relations, and tasks. However, existing models and benchmarks are commonly tailored to specific tasks, falling short of capturing the full complexity of online shopping. Large Language Models (LLMs), with their multi-task and few-shot learning abilities, have the potential to profoundly transform online shopping by alleviating task-specific engineering efforts and by providing users with interactive conversations. Despite the potential, LLMs face unique challenges in online shopping, such as domain-specific concepts, implicit knowledge, and heterogeneous user behaviors. Motivated by the potential and challenges, we propose Shopping MMLU, a diverse multi-task online shopping benchmark derived from real-world Amazon data. Shopping MMLU consists of 57 tasks covering 4 major shopping skills: concept understanding, knowledge reasoning, user behavior alignment, and multi-linguality, and can thus comprehensively evaluate the abilities of LLMs as general shop assistants. With Shoppping MMLU, we benchmark over 20 existing LLMs and uncover valuable insights about practices and prospects of building versatile LLM-based shop assistants. Shopping MMLU can be publicly accessed at https: //github. com/KL4805/ShoppingMMLU. In addition, with Shopping MMLU, we are hosting a competition in KDD Cup 2024 with over 500 participating teams. The winning solutions and the associated workshop can be accessed at our website https: //amazon-kddcup24. github. io/.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Task-Adaptive Prompted Transformer for Cross-Domain Few-Shot Learning

  • Jiamin Wu
  • Xin Liu
  • Xiaotian Yin
  • Tianzhu Zhang
  • Yongdong Zhang

Cross-Domain Few-Shot Learning (CD-FSL) aims at recognizing samples in novel classes from unseen domains that are vastly different from training classes, with few labeled samples. However, the large domain gap between training and novel classes makes previous FSL methods perform poorly. To address this issue, we propose MetaPrompt, a Task-adaptive Prompted Transformer model for CD-FSL, by jointly exploiting prompt learning and the parameter generation framework. The proposed MetaPrompt enjoys several merits. First, a task-conditioned prompt generator is established upon attention mechanisms. It can flexibly produce a task-adaptive prompt with arbitrary length for unseen tasks, by selectively gathering task characteristics from the contextualized support embeddings. Second, the task-adaptive prompt is attached to Vision Transformer to facilitate fast task adaptation, steering the task-agnostic representation to incorporate task knowledge. To our best knowledge, this is the first work to exploit a prompt-based parameter generation mechanism for CD-FSL. Extensive experimental results on the Meta-Dataset benchmark demonstrate that our method achieves superior results against state-of-the-art methods.

PDF Details DOI

JMLR Journal 2023 Journal Article

An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity

  • Wei Liu
  • Xin Liu
  • Xiaojun Chen

The leaky ReLU network with a group sparse regularization term has been widely used in the recent years. However, training such network yields a nonsmooth nonconvex optimization problem and there exists a lack of approaches to compute a stationary point deterministically. In this paper, we first resolve the multi-layer composite term in the original optimization problem by introducing auxiliary variables and additional constraints. We show the new model has a nonempty and bounded solution set and its feasible set satisfies the Mangasarian-Fromovitz constraint qualification. Moreover, we show the relationship between the new model and the original problem. Remarkably, we propose an inexact augmented Lagrangian algorithm for solving the new model, and show the convergence of the algorithm to a KKT point. Numerical experiments demonstrate that our algorithm is more efficient for training sparse leaky ReLU neural networks than some well-known algorithms. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

NeurIPS Conference 2023 Conference Paper

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

  • Jiaxin Bai
  • Xin Liu
  • Weiqi Wang
  • Chen Luo
  • Yangqiu Song

Querying knowledge graphs (KGs) using deep learning approaches can naturally leverage the reasoning and generalization ability to learn to infer better answers. Traditional neural complex query answering (CQA) approaches mostly work on entity-centric KGs. However, in the real world, we also need to make logical inferences about events, states, and activities (i. e. , eventualities or situations) to push learning systems from System I to System II, as proposed by Yoshua Bengio. Querying logically from an EVentuality-centric KG (EVKG) can naturally provide references to such kind of intuitive and logical inference. Thus, in this paper, we propose a new framework to leverage neural methods to answer complex logical queries based on an EVKG, which can satisfy not only traditional first-order logic constraints but also implicit logical constraints over eventualities concerning their occurrences and orders. For instance, if we know that Food is bad happens before PersonX adds soy sauce, then PersonX adds soy sauce is unlikely to be the cause of Food is bad due to implicit temporal constraint. To facilitate consistent reasoning on EVKGs, we propose Complex Eventuality Query Answering (CEQA), a more rigorous definition of CQA that considers the implicit logical constraints governing the temporal order and occurrence of eventualities. In this manner, we propose to leverage theorem provers for constructing benchmark datasets to ensure the answers satisfy implicit logical constraints. We also propose a Memory-Enhanced Query Encoding (MEQE) approach to significantly improve the performance of state-of-the-art neural query encoders on the CEQA task.

PDF Details

NeurIPS Conference 2023 Conference Paper

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

  • Xin Liu
  • Zheng Li
  • Yifan Gao
  • Jingfeng Yang
  • Tianyu Cao
  • Zhengyang Wang
  • Bing Yin
  • Yangqiu Song

The goal of session-based recommendation in E-commerce is to predict the next item that an anonymous user will purchase based on the browsing and purchase history. However, constructing global or local transition graphs to supplement session data can lead to noisy correlations and user intent vanishing. In this work, we propose the Frequent Attribute Pattern Augmented Transformer (FAPAT) that characterizes user intents by building attribute transition graphs and matching attribute patterns. Specifically, the frequent and compact attribute patterns are served as memory to augment session representations, followed by a gate and a transformer block to fuse the whole session information. Through extensive experiments on two public benchmarks and 100 million industrial data in three domains, we demonstrate that FAPAT consistently outperforms state-of-the-art methods by an average of 4. 5% across various evaluation metrics (Hits, NDCG, MRR). Besides evaluating the next-item prediction, we estimate the models' capabilities to capture user intents via predicting items' attributes and period-item recommendations.

PDF Details

EAAI Journal 2023 Journal Article

Forecasting the eddy current loss of a large turbo generator using hybrid ensemble Gaussian process regression

  • Jingying Zhao
  • Yifan Song
  • Likun Wang
  • Hai Guo
  • Fabrizio Marigentti
  • Xin Liu

For the issue that the sample space of wedge winding eddy current losses of large generator does not obey Gaussian distribution, a hybrid ensemble Gaussian process regression (HEGPR) model is proposed in this paper. The HEGPR contains three layers. First, four tree regression models (XGBoost, CatBoost, LGBM and NGBoost) are built. Then, the output of the first layer is taken as the input of multiple Gaussian regression models, so that the input samples of the second layer obey Gaussian distribution, which can effectively improve the generalization ability of Gaussian process regression. The results show that the root mean squared error (RMSE) is 0. 0282 and the goodness of fit ( R 2 ) is 0. 9973. The model has good prediction performance for the eddy current loss of large turbo generator. Compared with kinds of Gaussian process models and traditional ensemble learning models, the prediction accuracy of this model is higher, and it is more suitable for forecasting eddy current loss of the large generator. HEGPR model can effectively solve the problem of insufficient regression accuracy of Gaussian process when sample space does not obey Gaussian distribution.

Details DOI

IROS Conference 2023 Conference Paper

Look Before You Drive: Boosting Trajectory Forecasting via Imagining Future

  • Yixuan Fan
  • Xin Liu
  • Yali Li 0001
  • Shengjin Wang

Predicting the future trajectories of other agents in the scene fast and effectively is crucial for autonomous driving systems. We note that high-quality predictions require us to take into account the subjective initiative of the target agents, which is reflected by the fact that they themselves make decisions based on their own predictions about the future, just like our ego vehicle's prediction-planning system. However, this characteristic has been neglected in previous studies. We introduce Look Before You Drive (LBYD), a two-stage approach that explicitly incorporates both past observations and future estimates to make predictions. To get a preliminary estimate of the future, we propose a neat and effective baseline capable of making predictions for multiple agents simultaneously. We use only the most basic structures, mainly Transformer, to ensure sufficient inference speed and room for expansion. On this basis, we cooperatively train two networks to enable the coarse estimates to boost final forecasting. Our experiments demonstrate that LBYD can significantly surpass the baseline performance. Moreover, while state-of-the-art methods rely on considering heterogeneity and artificially designed inductive biases for attention modeling, LBYD performs on par with SOTA without them on both the Argoverse 1 and the large scale Argoverse 2 datasets, and can run at 67 FPS on an RTX 3090 GPU.

Details

NeurIPS Conference 2023 Conference Paper

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

  • Hejie Cui
  • Xinyu Fang
  • Zihan Zhang
  • Ran Xu
  • Xuan Kan
  • Xin Liu
  • Yue Yu
  • Manling Li

Images contain rich relational knowledge that can help machines understand the world. Existing methods on visual knowledge extraction often rely on the pre-defined format (e. g. , sub-verb-obj tuples) or vocabulary (e. g. , relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction. To achieve this, we present OpenVik which consists of an open relational region detector to detect regions potentially containing relational knowledge and a visual knowledge generator that generates format-free knowledge by prompting the large multimodality model with the detected region of interest. We also explore two data enhancement techniques for diversifying the generated format-free visual knowledge. Extensive knowledge quality evaluations highlight the correctness and uniqueness of the extracted open visual knowledge by OpenVik. Moreover, integrating our extracted knowledge across various visual reasoning applications shows consistent improvements, indicating the real-world applicability of OpenVik.

PDF Details

EAAI Journal 2023 Journal Article

Randomized block-coordinate adaptive algorithms for nonconvex optimization problems

  • Yangfan Zhou
  • Kaizhu Huang
  • Jiang Li
  • Cheng Cheng
  • Xuguang Wang
  • Amir Hussian
  • Xin Liu

Nonconvex optimization problems have always been one focus in deep learning, in which many fast adaptive algorithms based on momentum are applied. However, the full gradient computation of high-dimensional feature vector in the above tasks become prohibitive. To reduce the computation cost for optimizers on nonconvex optimization problems typically seen in deep learning, this work proposes a randomized block-coordinate adaptive optimization algorithm, named RAda, which randomly picks a block from the full coordinates of the parameter vector and then sparsely computes its gradient. We prove that RAda converges to a δ -accurate solution with the stochastic first-order complexity of O ( 1 / δ 2 ), where δ is the upper bound of the gradient’s square, under nonconvex cases. Experiments on public datasets including CIFAR-10, CIFAR-100, and Penn TreeBank, verify that RAda outperforms the other compared algorithms in terms of the computational cost.

Details DOI

NeurIPS Conference 2023 Conference Paper

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

  • Yijia Cheng
  • Xin Liu
  • Jingyu Yang

Capturing screen contents by smartphone cameras has become a common way for information sharing. However, these images and videos are often degraded by moiré patterns, which are caused by frequency aliasing between the camera filter array and digital display grids. We observe that the moiré patterns in raw domain is simpler than those in sRGB domain, and the moiré patterns in raw color channels have different properties. Therefore, we propose an image and video demoiréing network tailored for raw inputs. We introduce a color-separated feature branch, and it is fused with the traditional feature-mixed branch via channel and spatial modulations. Specifically, the channel modulation utilizes modulated color-separated features to enhance the color-mixed features. The spatial modulation utilizes the feature with large receptive field to modulate the feature with small receptive field. In addition, we build the first well-aligned raw video demoiréing (RawVDemoiré) dataset and propose an efficient temporal alignment method by inserting alternating patterns. Experiments demonstrate that our method achieves state-of-the-art performance for both image and video demoiréing. Our dataset and code will be released after the acceptance of this work.

PDF Details

IJCAI Conference 2023 Conference Paper

Recognizable Information Bottleneck

  • Yilin Lyu
  • Xin Liu
  • Mingyang Song
  • Xinyue Wang
  • Yaxin Peng
  • Tieyong Zeng
  • Liping Jing

Information Bottlenecks (IBs) learn representations that generalize to unseen data by information compression. However, existing IBs are practically unable to guarantee generalization in real-world scenarios due to the vacuous generalization bound. The recent PAC-Bayes IB uses information complexity instead of information compression to establish a connection with the mutual information generalization bound. However, it requires the computation of expensive second-order curvature, which hinders its practical application. In this paper, we establish the connection between the recognizability of representations and the recent functional conditional mutual information (f-CMI) generalization bound, which is significantly easier to estimate. On this basis we propose a Recognizable Information Bottleneck (RIB) which regularizes the recognizability of representations through a recognizability critic optimized by density ratio matching under the Bregman divergence. Extensive experiments on several commonly used datasets demonstrate the effectiveness of the proposed method in regularizing the model and estimating the generalization gap.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

rPPG-Toolbox: Deep Remote PPG Toolbox

  • Xin Liu
  • Girish Narayanswamy
  • Akshay Paruchuri
  • Xiaoyu Zhang
  • Jiankai Tang
  • Yuzhe Zhang
  • Roni Sengupta
  • Shwetak Patel

Camera-based physiological measurement is a fast growing field of computer vision. Remote photoplethysmography (rPPG) utilizes imaging devices (e. g. , cameras) to measure the peripheral blood volume pulse (BVP) via photoplethysmography, and enables cardiac measurement via webcams and smartphones. However, the task is non-trivial with important pre-processing, modeling and post-processing steps required to obtain state-of-the-art results. Replication of results and benchmarking of new models is critical for scientific progress; however, as with many other applications of deep learning, reliable codebases are not easy to find or use. We present a comprehensive toolbox, rPPG-Toolbox, unsupervised and supervised rPPG models with support for public benchmark datasets, data augmentation and systematic evaluation: https: //github. com/ubicomplab/rPPG-Toolbox.

PDF Details

NeurIPS Conference 2023 Conference Paper

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

  • Honghao Wei
  • Xin Liu
  • Weina Wang
  • Lei Ying

This paper considers a class of reinforcement learning problems, which involve systems with two types of states: stochastic and pseudo-stochastic. In such systems, stochastic states follow a stochastic transition kernel while the transitions of pseudo-stochastic states are deterministic {\em given} the stochastic states/transitions. We refer to such systems as mixed systems, which are widely used in various applications, including Manufacturing systems, communication networks, and queueing networks. We propose a sample-efficient RL method that accelerates learning by generating augmented data samples. The proposed algorithm is data-driven (model-free), but it learns the policy from data samples from both real and augmented samples. This method significantly improves learning by reducing the sample complexity such that the dataset only needs to have sufficient coverage of the stochastic states. We analyze the sample complexity of the proposed method under Fitted Q Iteration (FQI) and demonstrate that the optimality gap decreases as $O\left(\sqrt{\frac{1}{n}}+\sqrt{\frac{1}{m}}\right), $ where $n$ represents the number of real samples, and $m$ is the number of augmented samples per real sample. It is important to note that without augmented samples, the optimality gap is $O(1)$ due to the insufficient data coverage of the pseudo-stochastic states. Our experimental results on multiple queueing network applications confirm that the proposed method indeed significantly accelerates both deep Q-learning and deep policy gradient.

PDF Details

AAAI Conference 2022 Conference Paper

A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes

  • Honghao Wei
  • Xin Liu
  • Lei Ying

This paper presents a model-free reinforcement learning (RL) algorithm for infinite-horizon average-reward Constrained Markov Decision Processes (CMDPs). Considering a learning horizon K, which is sufficiently large, the proposed algorithm achieves Õ √ SAκ δ K 5 6 regret and zero constraint violation, where S is the number of states, A is the number of actions, and κ and δ are two constants independent of the learning horizon K.

PDF Details

AIJ Journal 2022 Journal Article

ASER: Towards large-scale commonsense knowledge acquisition via higher-order selectional preference over eventualities

  • Hongming Zhang
  • Xin Liu
  • Haojie Pan
  • Haowen Ke
  • Jiefu Ou
  • Tianqing Fang
  • Yangqiu Song

Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to collect commonsense knowledge. In this paper, we propose to develop principles for collecting commonsense knowledge based on selectional preference, which is a common phenomenon in human languages that has been shown to be related to semantics. We generalize the definition of selectional preference from one-hop linguistic syntactic relations to higher-order relations over linguistic graphs. Unlike previous commonsense knowledge definitions (e. g. , ConceptNet), the selectional preference (SP) knowledge only relies on statistical distributions over linguistic graphs, which can be efficiently and accurately acquired from the unlabeled corpora with modern tools, rather than human-defined relations. As a result, acquiring SP knowledge is a much more scalable way of acquiring commonsense knowledge. Following this principle, we develop a large-scale eventuality (a linguistic term covering activity, state, and event)-based knowledge graph ASER, where each eventuality is represented as a dependency graph, and the relation between them is a discourse relation defined in shallow discourse parsing. The higher-order selectional preference over collected linguistic graphs reflects various kinds of commonsense knowledge. For example, dogs are more likely to bark than cats as the eventuality “dog barks” appears 14, 998 times in ASER while “cat barks” only appears 6 times. “Be hungry” is more likely to be the reason rather than result of “eat food” as the edge 〈“be hungry, ” Cause, “eat food”〉 appears in ASER while 〈“eat food, ” Cause, “be hungry”〉 does not. Moreover, motivated by the observation that humans understand events by abstracting the observed events to a higher level and can thus transfer their knowledge to new events, we propose a conceptualization module on top of the collected knowledge to significantly boost the coverage of ASER. In total, ASER contains 648 million edges between 438 million eventualities. After conceptualization with Probase, a selectional preference based concept-instance relational knowledge base, our concept graph contains 15 million conceptualized eventualities and 224 million edges between them. Detailed analysis is provided to demonstrate its quality. All the collected data, APIs, and tools that can help convert collected SP knowledge into the format of ConceptNet are available at https: //github. com/HKUST-KnowComp/ASER.

Details DOI

AAAI Conference 2022 Conference Paper

Diaformer: Automatic Diagnosis via Symptoms Sequence Generation

  • Junying Chen
  • Dongfang Li
  • Qingcai Chen
  • Wenxiu Zhou
  • Xin Liu

Automatic diagnosis has attracted increasing attention but remains challenging due to multi-step reasoning. Recent works usually address it by reinforcement learning methods. However, these methods show low efficiency and require taskspecific reward functions. Considering the conversation between doctor and patient allows doctors to probe for symptoms and make diagnoses, the diagnosis process can be naturally seen as the generation of a sequence including symptoms and diagnoses. Inspired by this, we reformulate automatic diagnosis as a symptoms Sequence Generation (SG) task and propose a simple but effective automatic Diagnosis model based on Transformer (Diaformer). We firstly design the symptom attention framework to learn the generation of symptom inquiry and the disease diagnosis. To alleviate the discrepancy between sequential generation and disorder of implicit symptoms, we further design three orderless training mechanisms. Experiments on three public datasets show that our model outperforms baselines on disease diagnosis by 1%, 6% and 11. 5% with the highest training efficiency. Detailed analysis on symptom inquiry prediction demonstrates that the potential of applying symptoms sequence generation for automatic diagnosis.

PDF Details

YNICL Journal 2022 Journal Article

Fast and equilibrium CEST imaging of brain tumor patients at 3T

  • Yin Wu
  • Zhou Liu
  • Qian Yang
  • Liyan Zou
  • Fan Zhang
  • Long Qian
  • Xin Liu
  • Hairong Zheng

Chemical exchange saturation transfer (CEST) MRI, versatile for detecting endogenous mobile proteins and tissue pH, has proved valuable in tumor imaging. However, CEST MRI scans are often performed under non-equilibrium conditions, which confound tissue characterization. This study proposed a quasi-steady-state (QUASS) CEST MRI algorithm to standardize fast and accurate tumor imaging at 3 T. The CEST signal evolution was modeled by longitudinal relaxation rate during relaxation delay (Td) and spinlock relaxation during RF saturation time (Ts), from which the QUASS CEST effect is derived. Numerical simulation and human MR imaging experiments (7 healthy volunteers and 19 tumor patients) were conducted at 3 T to compare the CEST measurements obtained under two representative experimental conditions. In addition, amide proton transfer (APT), combined magnetization transfer (MT) and nuclear overhauser enhancement (NOE) effects, and direct water saturation were isolated using a 3-pool Lorentzian fitting in white matter and gray matter of healthy volunteers and for patients in the contralateral normal-appearing white matter and tumor regions. Finally, the student's t-test was performed between conventional and QUASS CEST measurements. The routine APT and combined MT & NOE measures significantly varied with Ts and Td (P .05), indicating the accuracy and robustness of QUASS CEST MRI for tumor imaging. To summarize, the QUASS CEST reconstruction algorithm enables fast and accurate tumor CEST imaging at 3 T, promising to expedite and standardize clinical CEST MRI.

Details DOI

NeurIPS Conference 2022 Conference Paper

GLOBEM Dataset: Multi-Year Datasets for Longitudinal Human Behavior Modeling Generalization

  • Xuhai Xu
  • Han Zhang
  • Yasaman Sefidgar
  • Yiyi Ren
  • Xin Liu
  • Woosuk Seo
  • Jennifer Brown
  • Kevin Kuehn

Recent research has demonstrated the capability of behavior signals captured by smartphones and wearables for longitudinal behavior modeling. However, there is a lack of a comprehensive public dataset that serves as an open testbed for fair comparison among algorithms. Moreover, prior studies mainly evaluate algorithms using data from a single population within a short period, without measuring the cross-dataset generalizability of these algorithms. We present the first multi-year passive sensing datasets, containing over 700 user-years and 497 unique users’ data collected from mobile and wearable sensors, together with a wide range of well-being metrics. Our datasets can support multiple cross-dataset evaluations of behavior modeling algorithms’ generalizability across different users and years. As a starting point, we provide the benchmark results of 18 algorithms on the task of depression detection. Our results indicate that both prior depression detection algorithms and domain generalization techniques show potential but need further research to achieve adequate cross-dataset generalizability. We envision our multi-year datasets can support the ML community in developing generalizable longitudinal behavior modeling algorithms.

PDF Details

AAAI Conference 2022 Conference Paper

Graph Convolutional Networks with Dual Message Passing for Subgraph Isomorphism Counting and Matching

  • Xin Liu
  • Yangqiu Song

Graph neural networks (GNNs) and message passing neural networks (MPNNs) have been proven to be expressive for subgraph structures in many applications. Some applications in heterogeneous graphs require explicit edge modeling, such as subgraph isomorphism counting and matching. However, existing message passing mechanisms are not designed well in theory. In this paper, we start from a particular edge-tovertex transform and exploit the isomorphism property in the edge-to-vertex dual graphs. We prove that searching isomorphisms on the original graph is equivalent to searching on its dual graph. Based on this observation, we propose dual message passing neural networks (DMPNNs) to enhance the substructure representation learning in an asynchronous way for subgraph isomorphism counting and matching as well as unsupervised node classification. Extensive experiments demonstrate the robust performance of DMPNNs by combining both node and edge representation learning in synthetic and real heterogeneous graphs.

PDF Details

AAAI Conference 2022 Conference Paper

KGR4: Retrieval, Retrospect, Refine and Rethink for Commonsense Generation

  • Xin Liu
  • Dayiheng Liu
  • Baosong Yang
  • Haibo Zhang
  • Junwei Ding
  • Wenqing Yao
  • Weihua Luo
  • Haiying Zhang

Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since sentences they produce are often implausible and grammatically incorrect. In this paper, inspired by the process of humans creating sentences, we propose a novel Knowledgeenhanced Commonsense Generation framework, termed KGR4, consisting of four stages: Retrieval, Retrospect, Refine, Rethink. Under this framework, we first perform retrieval to search for relevant sentences from external corpus as the prototypes. Then, we train the generator that either edits or copies these prototypes to generate candidate sentences, of which potential errors will be fixed by an autoencoderbased refiner. Finally, we select the output sentence from candidate sentences produced by generators with different hyper-parameters. Experimental results and in-depth analysis on the CommonGen benchmark strongly demonstrate the effectiveness of our framework. Particularly, KGR4 obtains 33. 56 SPICE points in the official leaderboard, outperforming the previously-reported best result by 2. 49 SPICE points and achieving state-of-the-art performance. We release the code at https: //github. com/DeepLearnXMU/KGR-4.

PDF Details

AAAI Conference 2022 Conference Paper

Leaping through Time with Gradient-Based Adaptation for Recommendation

  • Nuttapong Chairatanakul
  • Hoang NT
  • Xin Liu
  • Tsuyoshi Murata

Modern recommender systems are required to adapt to the change in user preferences and item popularity. Such a problem is known as the temporal dynamics problem, and it is one of the main challenges in recommender system modeling. Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based metalearning to model time dependencies. LeapRec characterizes temporal dynamics by two complement components named global time leap (GTL) and ordered time leap (OTL). By design, GTL learns long-term patterns by finding the shortest learning path across unordered temporal data. Cooperatively, OTL learns short-term patterns by considering the sequential nature of the temporal data. Our experimental results show that LeapRec consistently outperforms the state-of-the-art methods on several datasets and recommendation metrics. Furthermore, we provide an empirical study of the interaction between GTL and OTL, showing the effects of long- and short-term modeling.

PDF Details

IS Journal 2022 Journal Article

Multiscale 3D-Shift Graph Convolution Network for Emotion Recognition From Human Actions

  • Henglin Shi
  • Wei Peng
  • Haoyu Chen
  • Xin Liu
  • Guoying Zhao

Emotion recognition from body gestures is challenging since similar emotions can be expressed by arbitrary spatial configurations of joints, which results in relying on modeling spatial-temporal patterns from a more global level. However, most recent powerful graph convolution networks (GCNs) separate the spatial and temporal modeling into isolated processes, where GCN models spatial interactions using partially fixed adjacent matrices and 1D convolution captures temporal dynamics, which is insufficient for emotion recognition. In this work, we propose the 3D-Shift GCN, which enables interactions of joints within a spatial-temporal volume for global feature extraction. Besides, we further develop a multiscale architecture, the MS-Shift GCN, to fuse features captured under different temporal ranges for modeling richer dynamics. After conducting evaluation on two regular action recognition benchmarks and two gesture based emotion recognition datasets, the results show that the proposed method outperforms several state-of-the-art methods.

Details DOI

NeurIPS Conference 2022 Conference Paper

Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and Beyond

  • Hengquan Guo
  • Xin Liu
  • Honghao Wei
  • Lei Ying

This paper considers online convex optimization with hard constraints and analyzes achievable regret and cumulative hard constraint violation (violation for short). The problem distinguishes itself from online convex optimization with soft constraints, where a violation at one round can be compensated/cancelled by a conservative decision at a different round. We propose a RECtified Online Optimization algorithm (RECOO) and consider two settings: fixed constraints and adversarial constraints. Both settings have been considered in the literature. Compared with existing results, {\em RECOO achieves the best of two worlds and beyond. } For the fixed-constraints setting, RECOO achieves $O\left(\sqrt{T}\right)$ regret and $O(1)$ violation, where $T$ is the learning horizon. The best known results in this case are $O(\sqrt{T})$ regret and $O\left(T^{1/4}\right)$ violation. For the adversarial-constraints setting, it guarantees $O(\sqrt{T})$ regret and $O(T^{3/4})$ violation, which match the best existing results. When the loss functions are strongly convex, RECOO can guarantee $O(\log T)$ regret and $O(1)$ violation for fixed constraints, and $O(\log T)$ regret and $O(\sqrt{T\log T})$ violation for adversarial constraints. Both these results are order-wise better than the existing bounds. The regret and violation bounds mentioned above use the best fixed decision in hindsight as the baseline. This paper further considers a dynamic baseline where the comparator sequence is time-varying. This paper shows that RECOO not only improves the existing results in the fixed-constraints setting but also {\em for the first time, } guarantees dynamic regret and violation bounds in the adversarial-constraints setting. Our experiment results confirm that RECOO outperforms several existing algorithms for both fixed and adversarial constraints.

PDF Details

NeurIPS Conference 2022 Conference Paper

SCAMPS: Synthetics for Camera Measurement of Physiological Signals

  • Daniel McDuff
  • Miah Wander
  • Xin Liu
  • Brian Hill
  • Javier Hernandez
  • Jonathan Lester
  • Tadas Baltrusaitis

The use of cameras and computational algorithms for noninvasive, low-cost and scalable measurement of physiological (e. g. , cardiac and pulmonary) vital signs is very attractive. However, diverse data representing a range of environments, body motions, illumination conditions and physiological states is laborious, time consuming and expensive to obtain. Synthetic data have proven a valuable tool in several areas of machine learning, yet are not widely available for camera measurement of physiological states. Synthetic data offer "perfect" labels (e. g. , without noise and with precise synchronization), labels that may not be possible to obtain otherwise (e. g. , precise pixel level segmentation maps) and provide a high degree of control over variation and diversity in the dataset. We present SCAMPS, a dataset of synthetics containing 2, 800 videos (1. 68M frames) with aligned cardiac and respiratory signals and facial action intensities. The RGB frames are provided alongside segmentation maps and precise descriptive statistics about the underlying waveforms, including inter-beat interval, heart rate variability, and pulse arrival time. Finally, we present baseline results training on these synthetic data and testing on real-world datasets to illustrate generalizability.

PDF Details

NeurIPS Conference 2022 Conference Paper

Self-Supervised Learning via Maximum Entropy Coding

  • Xin Liu
  • Zhongdao Wang
  • Ya-Li Li
  • Shengjin Wang

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks. Inspired by the principle of maximum entropy in information theory, we hypothesize that a generalizable representation should be the one that admits the maximum entropy among all plausible representations. To make the objective end-to-end trainable, we propose to leverage the minimal coding length in lossy data coding as a computationally tractable surrogate for the entropy, and further derive a scalable reformulation of the objective that allows fast computation. Extensive experiments demonstrate that MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking. Interestingly, we show that existing batch-wise and feature-wise self-supervised objectives could be seen equivalent to low-order approximations of MEC. Code and pre-trained models are available at https: //github. com/xinliu20/MEC.

PDF Details

IJCAI Conference 2022 Conference Paper

Survey on Graph Neural Network Acceleration: An Algorithmic Perspective

  • Xin Liu
  • Mingyu Yan
  • Lei Deng
  • Guoqi Li
  • Xiaochun Ye
  • Dongrui Fan
  • Shirui Pan
  • Yuan Xie

Graph neural networks (GNNs) have been a hot spot of recent research and are widely utilized in diverse applications. However, with the use of huger data and deeper models, an urgent demand is unsurprisingly made to accelerate GNNs for more efficient execution. In this paper, we provide a comprehensive survey on acceleration methods for GNNs from an algorithmic perspective. We first present a new taxonomy to classify existing acceleration methods into five categories. Based on the classification, we systematically discuss these methods and highlight their correlations. Next, we provide comparisons from aspects of the efficiency and characteristics of these methods. Finally, we suggest some promising prospects for future research.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation

  • Yichen Zhu
  • Ning Liu
  • Zhiyuan Xu
  • Xin Liu
  • Weibin Meng
  • Louis Wang
  • Zhicai Ou
  • Jian Tang

Knowledge distillation (KD) can effectively compress neural networks by training a smaller network (student) to simulate the behavior of a larger one (teacher). A counter-intuitive observation is that a more expansive teacher does not make a better student, but the reasons for this phenomenon remain unclear. In this paper, we demonstrate that this is directly attributed to the presence of \textit{undistillable classes}: when trained with distillation, the teacher's knowledge of some classes is incomprehensible to the student model. We observe that while KD improves the overall accuracy, it is at the cost of the model becoming inaccurate in these undistillable classes. After establishing their widespread existence in state-of-the-art distillation methods, we illustrate their correlation with the capacity gap between teacher and student models. Finally, we present a simple Teach Less Learn More (TLLM) framework to identify and discard the undistillable classes during training. We validate the effectiveness of our approach on multiple datasets with varying network architectures. In all settings, our proposed method is able to exceed the performance of competitive state-of-the-art techniques.

PDF Details

NeurIPS Conference 2021 Conference Paper

An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints

  • Xin Liu
  • Bin Li
  • Pengyi Shi
  • Lei Ying

This paper considers stochastic linear bandits with general nonlinear constraints. The objective is to maximize the expected cumulative reward over horizon $T$ subject to a set of constraints in each round $\tau\leq T$. We propose a pessimistic-optimistic algorithm for this problem, which is efficient in two aspects. First, the algorithm yields $\tilde{\cal O}\left(\left(\frac{K^{0. 75}}{\delta}+d\right)\sqrt{\tau}\right)$ (pseudo) regret in round $\tau\leq T, $ where $K$ is the number of constraints, $d$ is the dimension of the reward feature space, and $\delta$ is a Slater's constant; and {\em zero} constraint violation in any round $\tau>\tau', $ where $\tau'$ is {\em independent} of horizon $T. $ Second, the algorithm is computationally efficient. Our algorithm is based on the primal-dual approach in optimization and includes two components. The primal component is similar to unconstrained stochastic linear bandits (our algorithm uses the linear upper confidence bound algorithm (LinUCB)). The computational complexity of the dual component depends on the number of constraints, but is independent of the sizes of the contextual space, the action space, and the feature space. Thus, the computational complexity of our algorithm is similar to LinUCB for unconstrained stochastic linear bandits.

PDF Details

AAAI Conference 2021 Conference Paper

Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans

  • Xin He
  • Shihao Wang
  • Xiaowen Chu
  • Shaohuai Shi
  • Jiangping Tang
  • Xin Liu
  • Chenggang Yan
  • Jiyong Zhang

The COVID-19 pandemic has spread globally for several months. Because its transmissibility and high pathogenicity seriously threaten people’s lives, it is crucial to accurately and quickly detect COVID-19 infection. Many recent studies have shown that deep learning (DL) based solutions can help detect COVID-19 based on chest CT scans. However, most existing work focuses on 2D datasets, which may result in low quality models as the real CT scans are 3D images. Besides, the reported results span a broad spectrum on different datasets with a relatively unfair comparison. In this paper, we first use three state-of-the-art 3D models (ResNet3D101, DenseNet3D121, and MC3 18) to establish the baseline performance on three publicly available chest CT scan datasets. Then we propose a differentiable neural architecture search (DNAS) framework to automatically search the 3D DL models for 3D chest CT scans classification and use the Gumbel Softmax technique to improve the search efficiency. We further exploit the Class Activation Mapping (CAM) technique on our models to provide the interpretability of the results. The experimental results show that our searched models (CovidNet3D) outperform the baseline human-designed models on three datasets with tens of times smaller model size and higher accuracy. Furthermore, the results also verify that CAM can be well applied in CovidNet3D for COVID- 19 datasets to provide interpretability for medical diagnosis. Code: https: //github. com/HKBU-HPML/CovidNet3D.

PDF Details

AAAI Conference 2021 Conference Paper

Enhancing Audio-Visual Association with Self-Supervised Curriculum Learning

  • Jingran Zhang
  • Xing Xu
  • Fumin Shen
  • Huimin Lu
  • Xin Liu
  • Heng Tao Shen

The recent success of audio-visual representations learning can be largely attributed to their pervasive concurrency property, which can be used as a self-supervision signal and extract correlation information. While most recent works focus on capturing the shared associations between the audio and visual modalities, they rarely consider multiple audio and video pairs at once and pay little attention to exploiting the valuable information within each modality. To tackle this problem, we propose a novel audio-visual representation learning method dubbed self-supervised curriculum learning (SSCL) under the teacher-student learning manner. Specifically, taking advantage of contrastive learning, a twostage scheme is exploited, which transfers the cross-modal information between teacher and student model as a phased process. The proposed SSCL approach regards the pervasive property of audiovisual concurrency as latent supervision and mutually distills the structure knowledge of visual to audio data. Notably, the SSCL method can learn discriminative audio and visual representations for various downstream applications. Extensive experiments conducted on both action video recognition and audio sound recognition tasks show the remarkably improved performance of the SSCL method compared with the state-of-the-art self-supervised audio-visual representation learning methods.

PDF Details

JBHI Journal 2021 Journal Article

Learning a Deep CNN Denoising Approach Using Anatomical Prior Information Implemented With Attention Mechanism for Low-Dose CT Imaging on Clinical Patient Data From Multiple Anatomical Sites

  • Zhenxing Huang
  • Xinfeng Liu
  • Rongpin Wang
  • Zixiang Chen
  • Yongfeng Yang
  • Xin Liu
  • Hairong Zheng
  • Dong Liang

Dose reduction in computed tomography (CT) has gained considerable attention in clinical applications because it decreases radiation risks. However, a lower dose generates noise in low-dose computed tomography (LDCT) images. Previous deep learning (DL)-based works have investigated ways to improve diagnostic performance to address this ill-posed problem. However, most of them disregard the anatomical differences among different human body sites in constructing the mapping function between LDCT images and their high-resolution normal-dose CT (NDCT) counterparts. In this article, we propose a novel deep convolutional neural network (CNN) denoising approach by introducing information of the anatomical prior. Instead of designing multiple networks for each independent human body anatomical site, a unified network framework is employed to process anatomical information. The anatomical prior is represented as a pattern of weights of the features extracted from the corresponding LDCT image in an anatomical prior fusion module. To promote diversity in the contextual information, a spatial attention fusion mechanism is introduced to capture many local regions of interest in the attention fusion module. Although many network parameters are saved, the experimental results demonstrate that our method, which incorporates anatomical prior information, is effective in denoising LDCT images. Furthermore, the anatomical prior fusion module could be conveniently integrated into other DL-based methods and avails the performance improvement on multiple anatomical data.

Details DOI

YNIMG Journal 2021 Journal Article

Longitudinal fMRI measures of cortical reactivation and hand use with and without training after sensory loss in primates

  • Hui-Xin Qi
  • Jamie L. Reed
  • Feng Wang
  • Christopher L. Gross
  • Xin Liu
  • Li Min Chen
  • Jon H. Kaas

In a series of previous studies, we demonstrated that damage to the dorsal column in the cervical spinal cord deactivates the contralateral somatosensory hand cortex and impairs hand use in a reach-to-grasp task in squirrel monkeys. Nevertheless, considerable cortical reactivation and behavioral recovery occurs over the following weeks to months after lesion. This timeframe may also be a window for targeted therapies to promote cortical reactivation and functional reorganization, aiding in the recovery process. Here we asked if and how task specific training of an impaired hand would improve behavioral recovery and cortical reorganization in predictable ways, and if recovery related cortical changes would be detectable using noninvasive functional magnetic resonance imaging (fMRI). We further asked if invasive neurophysiological mapping reflected fMRI results. A reach-to-grasp task was used to test impairment and recovery of hand use before and after dorsal column lesions (DC-lesion). The activation and organization of the affected primary somatosensory cortex (area 3b) was evaluated with two types of fMRI - either blood oxygenation level dependent (BOLD) or cerebral blood volume (CBV) with a contrast agent of monocrystalline iron oxide nanocolloid (MION) - before and after DC-lesion. At the end of the behavioral and fMRI studies, microelectrode recordings in the somatosensory areas 3a, 3b and 1 were used to characterize neuronal responses and verify the somatotopy of cortical reactivations. Our results indicate that even after nearly complete DC lesions, monkeys had both considerable post-lesion behavioral recovery, as well as cortical reactivation assessed with fMRI followed by extracellular recordings. Generalized linear regression analyses indicate that lesion extent is correlated with the behavioral outcome, as well as with the difference in the percent signal change from pre-lesion peak activation in fMRI. Monkeys showed behavioral recovery and nearly complete cortical reactivation by 9-12 weeks post-lesion (particularly when the DC-lesion was incomplete). Importantly, the specific training group revealed trends for earlier behavioral recovery and had higher magnitude of fMRI responses to digit stimulation by 5-8 weeks post-lesion. Specific kinematic measures of hand movements in the selected retrieval task predicted recovery time and related to lesion characteristics better than overall task performance success. For measures of cortical reactivation, we found that CBV scans provided stronger signals to vibrotactile digit stimulation as compared to BOLD scans, and thereby may be the preferred non-invasive way to study the cortical reactivation process after sensory deprivations from digits. When the reactivation of cortex for each of the digits was considered, the reactivation by digit 2 stimulation as measured with microelectrode maps and fMRI maps was best correlated with overall behavioral recovery.

Details DOI

IJCAI Conference 2021 Conference Paper

Policy Learning with Constraints in Model-free Reinforcement Learning: A Survey

  • Yongshuai Liu
  • Avishai Halev
  • Xin Liu

Reinforcement Learning (RL) algorithms have had tremendous success in simulated domains. These algorithms, however, often cannot be directly applied to physical systems, especially in cases where there are constraints to satisfy (e. g. to ensure safety or limit resource consumption). In standard RL, the agent is incentivized to explore any policy with the sole goal of maximizing reward; in the real world, however, ensuring satisfaction of certain constraints in the process is also necessary and essential. In this article, we overview existing approaches addressing constraints in model-free reinforcement learning. We model the problem of learning with constraints as a Constrained Markov Decision Process and consider two main types of constraints: cumulative and instantaneous. We summarize existing approaches and discuss their pros and cons. To evaluate policy performance under constraints, we introduce a set of standard benchmarks and metrics. We also summarize limitations of current methods and present open questions for future research.

PDF Details DOI

AAAI Conference 2020 Conference Paper

A Robust Adversarial Training Approach to Machine Reading Comprehension

  • Kai Liu
  • Xin Liu
  • An Yang
  • Jing Liu
  • Jinsong Su
  • Sujian Li
  • Qiaoqiao She

Lacking robustness is a serious problem for Machine Reading Comprehension (MRC) models. To alleviate this problem, one of the most promising ways is to augment the training dataset with sophisticated designed adversarial examples. Generally, those examples are created by rules according to the observed patterns of successful adversarial attacks. Since the types of adversarial examples are innumerable, it is not adequate to manually design and enrich training data to defend against all types of adversarial attacks. In this paper, we propose a novel robust adversarial training approach to improve the robustness of MRC models in a more generic way. Given an MRC model well-trained on the original dataset, our approach dynamically generates adversarial examples based on the parameters of current model and further trains the model by using the generated examples in an iterative schedule. When applied to the state-of-the-art MRC models, including QANET, BERT and ERNIE2. 0, our approach obtains significant and comprehensive improvements on 5 adversarial datasets constructed in different ways, without sacrificing the performance on the original SQuAD development set. Moreover, when coupled with other data augmentation strategy, our approach further boosts the overall performance on adversarial datasets and outperforms the state-of-the-art methods.

PDF Details

IJCAI Conference 2020 Conference Paper

An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension

  • Xin Liu
  • Kai Liu
  • Xiang Li
  • Jinsong Su
  • Yubin Ge
  • Bin Wang
  • Jiebo Luo

The lack of sufficient training data in many domains, poses a major challenge to the construction of domain-specific machine reading comprehension (MRC) models with satisfying performance. In this paper, we propose a novel iterative multi-source mutual knowledge transfer framework for MRC. As an extension of the conventional knowledge transfer with one-to-one correspondence, our framework focuses on the many-to-many mutual transfer, which involves synchronous executions of multiple many-to-one transfers in an iterative manner. Specifically, to update a target-domain MRC model, we first consider other domain-specific MRC models as individual teachers, and employ knowledge distillation to train a multi-domain MRC model, which is differentially required to fit the training data and match the outputs of these individual models according to their domain-level similarities to the target domain. After being initialized by the multi-domain MRC model, the target-domain MRC model is fine-tuned to match both its training data and the output of its previous best model simultaneously via knowledge distillation. Compared with previous approaches, our framework can continuously enhance all domain-specific MRC models by enabling each model to iteratively and differentially absorb the domain-shared knowledge from others. Experimental results and in-depth analyses on several benchmark datasets demonstrate the effectiveness of our framework.

PDF Details DOI

JBHI Journal 2020 Journal Article

Blockchain-Enabled Contextual Online Learning Under Local Differential Privacy for Coronary Heart Disease Diagnosis in Mobile Edge Computing

  • Xin Liu
  • Pan Zhou
  • Tie Qiu
  • Dapeng Oliver Wu

Due to the increasing medical data for coronary heart disease (CHD) diagnosis, how to assist doctors to make proper clinical diagnosis has attracted considerable attention. However, it faces many challenges, including personalized diagnosis, high dimensional datasets, clinical privacy concerns and insufficient computing resources. To handle these issues, we propose a novel blockchain-enabled contextual online learning model under local differential privacy for CHD diagnosis in mobile edge computing. Various edge nodes in the network can collaborate with each other to achieve information sharing, which guarantees that CHD diagnosis is suitable and reliable. To support the dynamically increasing dataset, we adopt a top-down tree structure to contain medical records which is partitioned adaptively. Furthermore, we consider patients’ contexts (e. g. , lifestyle, medical history records, and physical features) to provide more accurate diagnosis. Besides, to protect the privacy of patients and medical transactions without any trusted third party, we utilize the local differential privacy with randomised response mechanism and ensure blockchain-enabled information-sharing authentication under multi-party computation. Based on the theoretical analysis, we confirm that we provide real-time and precious CHD diagnosis for patients with sublinear regret, and achieve efficient privacy protection. The experimental results validate that our algorithm outperforms other algorithm benchmarks on running time, error rate and diagnosis accuracy.

Details DOI

AAAI Conference 2020 Conference Paper

IPO: Interior-Point Policy Optimization under Constraints

  • Yongshuai Liu
  • Jiaxin Ding
  • Xin Liu

In this paper, we study reinforcement learning (RL) algorithms to solve real-world decision problems with the objective of maximizing the long-term reward as well as satisfying cumulative constraints. We propose a novel first-order policy optimization method, Interior-point Policy Optimization (IPO), which augments the objective with logarithmic barrier functions, inspired by the interior-point method. Our proposed method is easy to implement with performance guarantees and can handle general types of cumulative multiconstraint settings. We conduct extensive evaluations to compare our approach with state-of-the-art baselines. Our algorithm outperforms the baseline algorithms, in terms of reward maximization and constraint satisfaction.

PDF Details

NeurIPS Conference 2020 Conference Paper

Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement

  • Xin Liu
  • Josh Fromm
  • Shwetak Patel
  • Daniel McDuff

Telehealth and remote health monitoring have become increasingly important during the SARS-CoV-2 pandemic and it is widely expected that this will have a lasting impact on healthcare practices. These tools can help reduce the risk of exposing patients and medical staff to infection, make healthcare services more accessible, and allow providers to see more patients. However, objective measurement of vital signs is challenging without direct contact with a patient. We present a video-based and on-device optical cardiopulmonary vital sign measurement approach. It leverages a novel multi-task temporal shift convolutional attention network (MTTS-CAN) and enables real-time cardiovascular and respiratory measurements on mobile platforms. We evaluate our system on an Advanced RISC Machine (ARM) CPU and achieve state-of-the-art accuracy while running at over 150 frames per second which enables real-time applications. Systematic experimentation on large benchmark datasets reveals that our approach leads to substantial (20%-50%) reductions in error and generalizes well across datasets.

PDF Details

IJCAI Conference 2020 Conference Paper

On the Importance of Word and Sentence Representation Learning in Implicit Discourse Relation Classification

  • Xin Liu
  • Jiefu Ou
  • Yangqiu Song
  • Xin Jiang

Implicit discourse relation classification is one of the most difficult parts in shallow discourse parsing as the relation prediction without explicit connectives requires the language understanding at both the text span level and the sentence level. Previous studies mainly focus on the interactions between two arguments. We argue that a powerful contextualized representation module, a bilateral multi-perspective matching module, and a global information fusion module are all important to implicit discourse analysis. We propose a novel model to combine these modules together. Extensive experiments show that our proposed model outperforms BERT and other state-of-the-art systems on the PDTB dataset by around 8% and CoNLL 2016 datasets around 16%. We also analyze the effectiveness of different modules in the implicit discourse relation classification task and demonstrate how different levels of representation learning can affect the results.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

AdaLinUCB: Opportunistic Learning for Contextual Bandits

  • Xueying Guo
  • Xiaoxiao Wang
  • Xin Liu

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in recommendations. When the exploration cost is low, so is the actual regret of pulling a sub-optimal arm (e. g. , trying a suboptimal recommendation). Therefore, intuitively, we could explore more when the exploration cost is relatively low and exploit more when the exploration cost is relatively high. Inspired by this intuition, for opportunistic contextual bandits with Linear payoffs, we propose an Adaptive Upper-Confidence-Bound algorithm (AdaLinUCB) to adaptively balance the exploration-exploitation trade-off for opportunistic learning. We prove that AdaLinUCB achieves O((log T)^2) problem-dependent regret upper bound, which has a smaller coefficient than that of the traditional LinUCB algorithm. Moreover, based on both synthetic and real-world dataset, we show that AdaLinUCB significantly outperforms other contextual bandit algorithms, under large exploration cost fluctuations.

PDF Details

ICRA Conference 2019 Conference Paper

Studies on Positioning Manipulators Actuated by Solid Media Transmissions

  • Haoran Zhao
  • Xin Liu
  • Rahul Korpu
  • Michael J. Heffernan
  • Aaron T. Becker
  • Nikolaos V. Tsekos

Fluidic transmission mechanisms use fluids to transmit force through conduits. We previously presented a transmission mechanism called solid-media transmission (SMT), which uses conduits filled with spheres and spacers for push-only bidirectional transmission. In this paper, we present new designs of SMT-actuated one-degree-of-freedom (DoF) and two-degree-of-freedom positioning manipulators, and report experiment studies to assess their performance. In these studies, closed-loop position control was performed with a PI controller and/or master-slave control. With braided PTFE tubing, SMT exhibited sub-millimeter accuracy, with a tolerance of ±0. 05 mm for the tested transmission lines with lengths up to 4m.

Details

JBHI Journal 2019 Journal Article

The Use of a Finger-Worn Accelerometer for Monitoring of Hand Use in Ambulatory Settings

  • Xin Liu
  • Smita Rajan
  • Nathan Ramasarma
  • Paolo Bonato
  • Sunghoon Ivan Lee

Objective assessment of stroke survivors' upper limb movements in ambulatory settings can provide clinicians with important information regarding the real impact of rehabilitation outside the clinic and help to establish individually-tailored therapeutic programs. This paper explores a novel approach to monitor the amount of hand use, which is relevant to the purposeful, goal-directed use of the limbs, based on a body networked sensor system composed of miniaturized fingerand wrist-worn accelerometers. The main contributions of this paper are twofold. First, this paper introduces and validates a new benchmark measurement of the amount of hand use based on data recorded by a motion capture system, the gold standard for human movement analysis. Second, this paper introduces a machine learning-based analytic pipeline that estimates the amount of hand use using data obtained from the wearable sensors and validates its estimation performance against the aforementioned benchmark measurement. Based on data collected from 18 neurologically intact individuals performing 11 motor tasks resembling various activities of daily living, the analytic results presented herein show that our new benchmark measure is reliable and responsive, and that the proposed wearable system can yield an accurate estimation of the amount of hand use (normalized root mean square error of 0. 11 and average Pearson correlation of 0. 78). This study has the potential to open up new research and clinical opportunities for monitoring hand function in ambulatory settings, ultimately enabling evidence-based, patient-centered rehabilitation and healthcare.

Details DOI

AAAI Conference 2018 Conference Paper

Action Recognition With Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion

  • Weiyao Lin
  • Chongyang Zhang
  • Ke Lu
  • Bin Sheng
  • Jianxin Wu
  • Bingbing Ni
  • Xin Liu
  • Hongkai Xiong

Action recognition is an important yet challenging task in computer vision. In this paper, we propose a novel deepbased framework for action recognition, which improves the recognition accuracy by: 1) deriving more precise features for representing actions, and 2) reducing the asynchrony between different information streams. We first introduce a coarse-to-fine network which extracts shared deep features at different action class granularities and progressively integrates them to obtain a more accurate feature representation for input actions. We further introduce an asynchronous fusion network. It fuses information from different streams by asynchronously integrating stream-wise features at different time points, hence better leveraging the complementary information in different streams. Experimental results on action recognition benchmarks demonstrate that our approach achieves the state-of-the-art performance.

PDF Details

IJCAI Conference 2018 Conference Paper

Biased Random Walk based Social Regularization for Word Embeddings

  • Ziqian Zeng
  • Xin Liu
  • Yangqiu Song

Nowadays, people publish a lot of natural language texts on social media. Socialized word embeddings (SWE) has been proposed to deal with two phenomena of language use: everyone has his/her own personal characteristics of language use and socially connected users are likely to use language in similar ways. We observe that the spread of language use is transitive. Namely, one user can affect his/her friends and the friends can also affect their friends. However, SWE modeled the transitivity implicitly. The social regularization in SWE only applies to one-hop neighbors and thus users outside the one-hop social circle will not be affected directly. In this work, we adopt random walk methods to generate paths on the social graph to model the transitivity explicitly. Each user on a path will be affected by his/her adjacent user(s) on the path. Moreover, according to the update mechanism of SWE, fewer friends a user has, fewer update opportunities he/she can get. Hence, we propose a biased random walk method to provide these users with more update opportunities. Experiments show that our random walk based social regularizations perform better on sentiment classification.

PDF Details

IJCAI Conference 2018 Conference Paper

Improving Maximum Likelihood Estimation of Temporal Point Process via Discriminative and Adversarial Learning

  • Junchi Yan
  • Xin Liu
  • Liangliang Shi
  • Changsheng Li
  • Hongyuan Zha

Point process is an expressive tool in learning temporal event sequence which is ubiquitous in real-world applications. Traditional predictive models are based on maximum likelihood estimation (MLE). This paper aims to improve MLE by discriminative and adversarial learning. The initial model is learned by MLE explaining the joint distribution of the occurred event history. Then it is refined by devising a gradient based learning procedure with two complementary recipes: i) mean square error (MSE) that directly reflects the prediction accuracy of the model; ii) adversarial classification loss which induces the Wasserstein distance loss. The hope is that the adversarial loss can add sharpness to the smooth effect inherently caused by the MSE loss. The method is generic and compatible with different differentiable parametric forms of the intensity function. Empirical results via a variant of the Hawkes processes demonstrate its effectiveness of our method.

PDF Details

IJCAI Conference 2017 Conference Paper

Learning User Dependencies for Recommendation

  • Yong Liu
  • Peilin Zhao
  • Xin Liu
  • Min Wu
  • Lixin Duan
  • Xiao-li Li

Social recommender systems exploit users' social relationships to improve recommendation accuracy. Intuitively, a user tends to trust different people regarding with different scenarios. Therefore, one main challenge of social recommendation is to exploit the most appropriate dependencies between users for a given recommendation task. Previous social recommendation methods are usually developed based on pre-defined user dependencies. Thus, they may not be optimal for a specific recommendation task. In this paper, we propose a novel recommendation method, named probabilistic relational matrix factorization (PRMF), which can automatically learn the dependencies between users to improve recommendation accuracy. In PRMF, users' latent features are assumed to follow a matrix variate normal (MVN) distribution. Both positive and negative user dependencies can be modeled by the row precision matrix of the MVN distribution. Moreover, we also propose an alternating optimization algorithm to solve the optimization problem of PRMF. Extensive experiments on four real datasets have been performed to demonstrate the effectiveness of the proposed PRMF model.

PDF Details

AAAI Conference 2017 Conference Paper

On Predictive Patent Valuation: Forecasting Patent Citations and Their Types

  • Xin Liu
  • Junchi Yan
  • Shuai Xiao
  • Xiangfeng Wang
  • Hongyuan Zha
  • Stephen Chu

Patents are widely regarded as a proxy for inventive output which is valuable and can be commercialized by various means. Individual patent information such as technology field, classification, claims, application jurisdictions are increasingly available as released by different venues. This work has relied on a long-standing hypothesis that the citation received by a patent is a proxy for knowledge flows or impacts of the patent thus is directly related to patent value. This paper does not fall into the line of intensive existing work that test or apply this hypothesis, rather we aim to address the limitation of using so-far received citations for patent valuation. By devising a point process based patent citation type aware (self-citation and non-self-citation) prediction model which incorporates the various information of a patent, we open up the possibility for performing predictive patent valuation which can be especially useful for newly granted patents with emerging technology. Study on real-world data corroborates the efficacy of our approach. Our initiative may also have policy implications for technology markets, patent systems and all other stakeholders. The code and curated data will be available to the research community.

PDF Details

NeurIPS Conference 2016 Conference Paper

Double Thompson Sampling for Dueling Bandits

  • Huasen Wu
  • Xin Liu

In this paper, we propose a Double Thompson Sampling (D-TS) algorithm for dueling bandit problems. As its name suggests, D-TS selects both the first and the second candidates according to Thompson Sampling. Specifically, D-TS maintains a posterior distribution for the preference matrix, and chooses the pair of arms for comparison according to two sets of samples independently drawn from the posterior distribution. This simple algorithm applies to general Copeland dueling bandits, including Condorcet dueling bandits as its special case. For general Copeland dueling bandits, we show that D-TS achieves $O(K^2 \log T)$ regret. Moreover, using a back substitution argument, we refine the regret to $O(K \log T + K^2 \log \log T)$ in Condorcet dueling bandits and many practical Copeland dueling bandits. In addition, we propose an enhancement of D-TS, referred to as D-TS+, that reduces the regret by carefully breaking ties. Experiments based on both synthetic and real-world data demonstrate that D-TS and D-TS$^+$ significantly improve the overall performance, in terms of regret and robustness.

PDF Details

IJCAI Conference 2016 Conference Paper

Exploring the Context of Locations for Personalized Location Recommendations

  • Xin Liu
  • Yong Liu
  • Xiaoli Li

Conventional location recommendation models rely on users' visit history, geographical influence, temporal influence, etc. , to infer users' preferences for locations. However, systematically modeling a location's context (i. e. , the set of locations visited before or after this location) is relatively unexplored. In this paper, by leveraging the Skip-gram model, we learn the latent representation for a location to capture the influence of its context. A pair-wise ranking loss that considers the confidences of observed user preferences for locations is then proposed to learn users' latent representations for personalized top-N location recommendations. Moreover, we also extend our model by taking into account temporal influence. Stochastic gradient descent based optimization algorithms are developed to fit the models. We conduct comprehensive experiments over four real datasets. Experimental results demonstrate that our approach significantly outperforms the state-of-the-art location recommendation methods.

PDF Details

NeurIPS Conference 2015 Conference Paper

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

  • Huasen Wu
  • R. Srikant
  • Xin Liu
  • Chong Jiang

We study contextual bandits with budget and time constraints under discrete contexts, referred to as constrained contextual bandits. The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time. To gain insight, we first study unit-cost systems with known context distribution. When the expected rewards are known, we develop an approximation of the oracle, referred to Adaptive-Linear-Programming(ALP), which achieves near-optimality and only requires the ordering of expected rewards. With these highly desirable features, we then combine ALP with the upper-confidence-bound (UCB) method in the general case where the expected rewards are unknown a priori. We show that the proposed UCB-ALP algorithm achieves logarithmic regret except in certain boundary cases. Further, we design algorithms and obtain similar regret analysis results for more general systems with unknown context distribution or heterogeneous costs. To the best of our knowledge, this is the first work that shows how to achieve logarithmic regret in constrained contextual bandits. Moreover, this work also sheds light on the study of computationally efficient algorithms for general constrained contextual bandits.

PDF Details

IJCAI Conference 2015 Conference Paper

Modeling Users' Dynamic Preference for Personalized Recommendation

  • Xin Liu

Modeling the evolution of users’ preference over time is essential for personalized recommendation. Traditional time-aware models like (1) timewindow or recency based approaches ignore or deemphasize much potentially useful information, and (2) time-aware collaborative filtering (CF) approaches largely rely on the information of other users, thus failing to precisely and comprehensively profile individual users for personalization. In this paper, for implicit feedback data, we propose a personalized recommendation model to capture users’ dynamic preference using Gaussian process. We first apply topic modeling to represent a user’s temporal preference in an interaction as a topic distribution. By aggregating such topic distributions of the user’s past interactions, we build her profile, where we treat each topic’s values at different interactions as a time series. Gaussian process is then applied to predict the user’s preference in the next interactions for top-N recommendation. Experiments conducted over two real datasets demonstrate that our approach outperforms the state-ofthe-art recommendation models by at least 42. 46% and 66. 14% in terms of precision and Mean Reciprocal Rank respectively.

PDF Details

IROS Conference 2015 Conference Paper

SPEAR: A monopedal robot with Switchable Parallel Elastic actuation

  • Xin Liu
  • Anthony Rossi
  • Ioannis Poulakakis

Inspired by biological systems, compliant elements are introduced in the driving train of legged robots with the purpose of recycling energy. This paper presents the design and control concept of the monopedal robot SPEAR, driven by a novel implementation of a Switchable Parallel Elastic Actuator (S-PEA). At the stance phase, the parallel spring in S-PEA works with the actuator to support body weight and recover energy. The spring is removed from the system at the flight phase to gain precise joint control. The stiffness of the whole leg is also adjustable online either by active control of the motor or by changing the knee angle at touchdown. Experimental results show that the spring recycles part of energy during hopping, reducing the peak torque and peak power of the motor.

Details

YNIMG Journal 2013 Journal Article

Locally linear embedding (LLE) for MRI based Alzheimer's disease classification

  • Xin Liu
  • Duygu Tosun
  • Michael W. Weiner
  • Norbert Schuff

Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. Specifically, we used the unsupervised learning algorithm of local linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions, while also utilizing the global nonlinear data structure. The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI. We tested the approach on 413 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had baseline MRI scans and complete clinical follow-ups over 3years with the following diagnoses: cognitive normal (CN; n=137), stable mild cognitive impairment (s-MCI; n=93), MCI converters to AD (c-MCI, n=97), and AD (n=86). We found that classifications using embedded MRI features generally outperformed (p<0. 05) classifications using the original features directly. Moreover, the improvement from LLE was not limited to a particular classifier but worked equally well for regularized logistic regressions, support vector machines, and linear discriminant analysis. Most strikingly, using LLE significantly improved (p=0. 007) predictions of MCI subjects who converted to AD and those who remained stable (accuracy/sensitivity/specificity: =0. 68/0. 80/0. 56). In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0. 56/0. 65/0. 46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD.

Details DOI

AAAI Conference 2012 Conference Paper

Modeling Context Aware Dynamic Trust Using Hidden Markov Model

  • Xin Liu
  • Anwitaman Datta

Modeling trust in complex dynamic environments is an important yet challenging issue since an intelligent agent may strategically change its behavior to maximize its profits. In this paper, we propose a context aware trust model to predict dynamic trust by using a Hidden Markov Model (HMM) to model an agent’s interactions. Although HMMs have already been applied in the past to model an agent’s dynamic behavior to greatly improve the traditional static probabilistic trust approaches, most HMM based trust models only focus on outcomes of the past interactions without considering interaction context, which we believe, reflects immensely on the dynamic behavior or intent of an agent. Interaction contextual information is comprehensively studied and integrated into the model to more precisely approximate an agent’s dynamic behavior. Evaluation using real auction data and synthetic data demonstrates the efficacy of our approach in comparison with previous state-of-the-art trust mechanisms.

PDF Details

IJCAI Conference 2011 Conference Paper

A Trust Prediction Approach Capturing Agents' Dynamic Behavior

  • Xin Liu
  • Anwitaman Datta

Predicting trust among the agents is of great importance to various open distributed settings (e. g. , e-market, peer-to-peer networks, etc. ) in that dishonest agents can easily join the system and achieve their goals by circumventing agreed rules, or gaining unfair advantages, etc. Most existing trust mechanisms derive trust by statistically investigating the target agent's historical information. However, even if rich historical information is available, it is challenging to model an agent's behavior since an intelligent agent may strategically change its behavior to maximize its profits. We therefore propose a trust prediction approach to capture dynamic behavior of the target agent. Specifically, we first identify features which are capable of describing/representing context of a transaction. Then we use these features to measure similarity between context of the potential transaction and that of previous transactions to estimate trustworthiness of the potential transaction based on previous similar transactions' outcomes. Evaluation using real auction data and synthetic data demonstrates efficacy of our approach in comparison with an existing representative trust mechanism.

PDF Details DOI
v2026.09.13