Yue Yu

AAAI Conference 2026 Conference Paper

Mitigating Entity Hallucinations in 3D Radiology Report Generation via Dual-Stream Alignment

• Lingyu Zhou
• Yue Yu
• Zhang Yi
• Xiuyuan Xu

Entity hallucination poses a major challenge in radiology report generation (RRG), particularly for 3D CT scans where complex spatial contexts amplify factual errors. To address this, medical entity phrases serve as key carriers for multi-modal prompting, integrating expert knowledge into the vision-language model. Current methods use unified cross-attention for volume-phrase alignment, failing to account for anatomical specificity during the alignment process. In this work, we introduce the Dual-stream Entity Alignment Reporting network (DEAR) that separately models organ and lesion entities to resolve anatomical bias. Specifically, the dual-stream entity aligner is designed to partition medical entity phrases into organ and lesion streams, feeding them into separate cross-attention blocks in parallel to achieve fine-grained volume–phrase alignment. For structurally regular and spatially stable organ entities, an organ-guided cross-attention (OGCA) block is proposed to enforce structural consistency by retrieving the top-k voxel tokens via volume–phrase similarity and preserving spatial connectivity through morphological dilation. Meanwhile, a lesion-guided cross-attention (LGCA) block is introduced for structurally irregular and spatially variable lesion entities, enhancing anomaly sensitivity through phrase-weighted attention and refining discriminative boundaries via 3D residual Laplacian filtering. Experiments demonstrate that DEAR significantly reduces entity hallucinations and improves clinical factuality in 3D RRG benchmarks.

EAAI Journal 2026 Journal Article

Power System state prediction method based on improved long short-term memory considering renewable energy uncertainty

• Yue Yu
• Chihan Zhou
• Yue Wang
• Tao Lu
• Ziqi Fan

To address the multi-dimensional uncertainty issues brought by high-penetration renewable energy sources grid integration, a power system state prediction method based on improved long short-term memory (LSTM) considering renewable energy uncertainty is proposed. First, a deep bidirectional long short-term memory neural network (Deep Bi-LSTM) is employed as the foundation of the Bayesian framework, capturing uncertainties in active distribution networks through posterior inference. Second, to address the limitations of the improved Deep Bi-LSTM model in feature extraction, an attention mechanism is introduced and a global-attention long short-term memory (GLSTM) model is constructed to strengthen the correlation between input features and target features. Finally, a novel state prediction method is proposed, which utilizes the GLSTM model to predict dynamic state variables, achieving overall modeling and quantification of both model uncertainty and aleatory uncertainty. Through simulation experiments conducted on IEEE 69-bus standard test systems, it is verified that the proposed Bayesian deep learning (BDL) method can effectively capture both types of uncertainties and achieve high-precision state prediction, providing a new feasible approach for the field of state prediction.

JBHI Journal 2026 Journal Article

Prior-Guided Selective Parameter Fine-Tuning for Source-Free Domain Adaptive Medical Image Segmentation

• Fanzhe Yan
• Gang Yang
• Xun Chen
• Yue Yu
• Aiping Liu

Source-free domain adaptation (SFDA) transfers knowledge from pre-trained source models to the un labeled target domain without accessing the private source data. Conventional SFDA methods for medical imageseg mentation typically depend on pseudo-label driven self training with full model fine-tuning. Although these methods have shown decent performance, the underlying principles remain insufficiently explored. In this work, we investigate SFDA through the PAC-Bayesian generalization error bound, demonstrating that its generalization error is jointly constrained by model complexity and pseudo-label noise. Motivated by this, we propose PATH, a selective PArameter fine-tuning framework guided by Topological and Historical priors for SFDA medical image segmentation. Specifically, PATH identifies domain-variant and task-distinctive parameters and sparsely updates them, thereby reducing effective model complexity during adaptation. In addition, PATH estimates pseudo-label reliability by integrating topological structure and historical prediction consistency priors to suppress pseudo-label noise. Extensive experiments on cross-scanner fundus image segmentation and cross modality abdominal multi-organ segmentation benchmarks demonstrate that PATH outperforms competing SFDA methods, achieving state-of-the-art performance. Code will be available at https://github.com/dogeONE-bit/PATH.

AAAI Conference 2026 Conference Paper

Symphony-MoE: Harmonizing Disparate Pre-trained Models into a Coherent Mixture-of-Experts

• Qi Wang
• Hanyang Peng
• Yue Yu

Mixture-of-Experts (MoE) models enable scalable performance by activating large parameter sets sparsely, minimizing computational overhead. To mitigate the prohibitive cost of training MoEs from scratch, recent work employs upcycling, reusing a single pre-trained dense model by replicating its feed-forward network (FFN) layers into experts. However, this limits expert diversity, as all experts originate from a single pre-trained dense model. This paper addresses this limitation by constructing powerful MoE models using experts sourced from multiple identically-architected but disparate pre-trained models (e.g., Qwen2.5-Coder and Qwen2). A key challenge lies in the fact that these source models occupy disparate, dissonant regions of the parameter space, making direct upcycling prone to severe performance degradation. To overcome this, we propose Symphony-MoE, a novel two-stage framework designed to harmonize these models into a single, coherent expert mixture. First, we establish this harmony in a training-free manner: we construct a shared backbone via a layer-aware fusion strategy and, crucially, alleviate parameter misalignment among experts using activation-based functional alignment. Subsequently, a stage of post-training coordinates the entire architecture. Experiments demonstrate that our method successfully integrates experts from heterogeneous sources, achieving an MoE model that significantly surpasses baselines in multi-domain tasks and out-of-distribution generalization.

NeurIPS Conference 2025 Conference Paper

AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforced Self-Play

• Ran Xu
• Yuchen Zhuang
• Zihan Dong
• Ruiyu Wang
• Yue Yu
• Joyce Ho
• Linjun Zhang
• Haoyu Wang

Search-augmented LLMs often struggle with complex reasoning tasks due to ineffective multi-hop retrieval and limited reasoning ability. We propose AceSearcher, a cooperative self-play framework that trains a single large language model (LLM) to alternate between two roles: a decomposer that breaks down complex queries and a solver that integrates retrieved contexts for answer generation. AceSearcher couples supervised fine-tuning on a diverse mixture of search, reasoning, and decomposition tasks with reinforcement fine-tuning optimized for final answer accuracy, eliminating the need for intermediate annotations. Extensive experiments on three reasoning-intensive tasks across 10 datasets show that AceSearcher outperforms state-of-the-art baselines, achieving an average exact match improvement of 7. 6%. Remarkably, on document-level finance reasoning tasks, AceSearcher-32B matches the performance of the giant DeepSeek-V3 model using less than 5% of iits parameters. Even at smaller scales (1. 5B and 8B), AceSearcher often surpasses existing search-augmented LLMs with up to 9× more parameters, highlighting its exceptional efficiency and effectiveness in tackling complex reasoning tasks.

AAAI Conference 2025 Conference Paper

Correcting Large Language Model Behavior via Influence Function

• Han Zhang
• Zhuo Zhang
• Yi Zhang
• Yuanzhao Zhai
• Hanyang Peng
• Yu Lei
• Yue Yu
• Hui Wang

Recent advancements in AI alignment techniques have significantly improved the alignment of large language models (LLMs) with static human preferences. However, the dynamic nature of human preferences can render some prior training data outdated or even erroneous, ultimately causing LLMs to deviate from contemporary human preferences and societal norms. Existing methodologies, either curation of new data for continual alignment or manual correction of outdated data for re-alignment, demand costly human resources. To address this, we propose a novel approach, LLM BehAvior Correction with INfluence FunCtion REcall and Post-Training (LANCET), which needs no human involvement. LANCET consists of two phases: (1) using a new method LinFAC to efficiently identify the training data that significantly impact undesirable model outputs, and (2) applying an novel Influence-driven Bregman Optimization (IBO) technique to adjust the model’s outputs based on these influence distributions. Our experiments show that LANCET effectively and efficiently corrects inappropriate behaviors of LLMs while preserving model utility. Further more, LANCET exhibits stronger generalization ability than all baselines under out-of-distribution harmful prompts, offering better interpretability and compatibility with real-world applications of LLMs.

YNICL Journal 2025 Journal Article

Corrigendum to “Disturbed hierarchy and mediation in reward-related circuits in depression”. [45 (2025) 103739]

• Ruikun Yang
• Junxia Chen
• Suping Yue
• Yue Yu
• Jiamin Fan
• Yuling Luo
• Hui He
• Mingjun Duan

YNICL Journal 2025 Journal Article

Disturbed hierarchy and mediation in reward-related circuits in depression

• Ruikun Yang
• Junxia Chen
• Suping Yue
• Yue Yu
• Jiamin Fan
• Yuling Luo
• Hui He
• Mingjun Duan

BACKGROUNDS/OBJECTIVE: Deep brain stimulation (DBS) has proved the viability of alleviating depression symptoms by stimulating deep reward-related nuclei. This study aims to investigate the abnormal connectivity profiles among superficial, intermediate, and deep brain regions within the reward circuit in major depressive disorder (MDD) and therefore provides references for identifying potential superficial cortical targets for non-invasive neuromodulation. METHODS: Resting-state functional magnetic resonance imaging data were collected from a cohort of depression patients (N = 52) and demographically matched healthy controls (N = 60). Utilizing existing DBS targets as seeds, we conducted step-wise functional connectivity (sFC) analyses to delineate hierarchical pathways linking to cerebral cortices. Subsequently, the mediation effects of cortical regions on the interaction within reward-related circuits were further explored by constructing mediation models. RESULTS: In both cohorts, sFC analysis revealed two reward-related pathways from the deepest DBS targets to intermediate regions including the thalamus, insula, and anterior cingulate cortex (ACC), then to the superficial cortical cortex including medial frontal cortex, posterior default mode network (pDMN), and right dorsolateral prefrontal cortex (DLPFC). Patients exhibited reduced sFC in bilateral thalamus and medial frontal cortex in short and long steps respectively compared to healthy controls. We also discovered the disappearance of the mediation effects of superficial cortical regions on the interaction between DBS targets and intermediate regions in reward-related pathways in patients with MDD. CONCLUSION: Our findings support abnormal hierarchical connectivity and mediation effects in reward-related brain regions at different depth levels in MDD, which might elucidate the underlying pathophysiological mechanisms and inspire novel targets for non-invasive interventions.

AAAI Conference 2025 Conference Paper

FaceA-Net: Facial Attribute-Driven ID Preserving Image Generation Network

• Jiayu Wang
• Yue Yu
• Jingjing Chen
• Qi Dai
• Yu-Gang Jiang

Recent advances in diffusion-based generative models have demonstrated superior performance in subject-driven image generation. Identity (ID) preserving image generation, as a subtask of subject-driven image generation, aims to generate customized images for specific human identity and has broad application potential. However, this task remains challenging due to the requirement for high ID fidelity and precise detail preservation. Additionally, generating high-quality context presents another challenge, as existing methods struggle to achieve both high ID fidelity and satisfactory context simultaneously. To address the issues of insufficient ID fidelity, we introduce a simple yet effective test-time fine-tuning approach. Specifically, we propose an attribute-driven training method that establishes global-level and local-level tasks to learn the global face feature and fine-grained attribute features, respectively. Furthermore, we introduce a novel ID-context decoupling framework that decouples image context generation from human ID generation, ensuring the quality of contextual content as well as facilitating the learning of ID information. Through extensive experiments, we demonstrate the effectiveness of the proposed method and showcase its capabilities across various applications.

ICLR Conference 2025 Conference Paper

GUI-World: A Video Benchmark and Dataset for Multimodal GUI-oriented Understanding

• Dongping Chen
• Yue Huang 0001
• Siyuan Wu 0001
• Jingyu Tang
• Huichi Zhou
• Qihui Zhang
• Zhigang He
• Yilin Bai

Recently, Multimodal Large Language Models (MLLMs) have been used as agents to control keyboard and mouse inputs by directly perceiving the Graphical User Interface (GUI) and generating corresponding commands. However, current agents primarily demonstrate strong understanding capabilities in static environments and are mainly applied to relatively simple domains, such as Web or mobile interfaces. We argue that a robust GUI agent should be capable of perceiving temporal information on the GUI, including dynamic Web content and multi-step tasks. Additionally, it should possess a comprehensive understanding of various GUI scenarios, including desktop software and multi-window interactions. To this end, this paper introduces a new dataset, termed GUI-World, which features meticulously crafted Human-MLLM annotations, extensively covering six GUI scenarios and eight types of GUI-oriented questions in three formats. We evaluate the capabilities of current state-of-the-art MLLMs, including Image LLMs and Video LLMs, in understanding various types of GUI content, especially dynamic and sequential content. Our findings reveal that current models struggle with dynamic GUI content without manually annotated keyframes or operation history. On the other hand, Video LLMs fall short in all GUI-oriented tasks given the sparse GUI video dataset. Therefore, we take the initial step of leveraging a fine-tuned Video LLM, GUI-Vid, as a GUI-oriented assistant, demonstrating an improved understanding of various GUI tasks. However, due to the limitations in the performance of base LLMs, we conclude that using video LLMs as GUI agents remains a significant challenge. We believe our work provides valuable insights for future research in dynamic GUI content understanding. All the dataset and code are publicly available at: https://gui-world.github.io.

NeurIPS Conference 2025 Conference Paper

Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data

• Tian Gao
• Songtao Lu
• Junkyu Lee
• Elliot Nelson
• Debarun Bhattacharjya
• Yue Yu
• Miao Liu

Causal discovery in the form of a directed acyclic graph (DAG) for dynamic time series data has been widely studied in various applications. Much of the existing work has focused on observational, offline, and/or stationary settings. In this work, we propose a dynamic DAG discovery algorithm, Meta-D$^2$AG, based on online meta-learning. Meta-D$^2$AG is designed to learn dynamic DAG structures from potentially nonlinear and non-stationary times series datasets, accounting for changes in both parameters and graph structures. Notably, Meta-D$^2$AG explicitly treats data collected at different time points with distribution shifts as distinct domains, which is assumed to occur as a result of external interventions. Moreover, Meta-D$^2$AG contains a new online meta-learning framework to take advantage of the temporal transition among existing domains such that it can quickly adapt to new domains with few measurements. A first-order optimization approach is utilized to efficiently solve the meta-learning framework, and theoretical analysis establishes the identifiability conditions and the convergence of the learning process. We demonstrate the promising performance of our method through better accuracy and sample efficiency on benchmark datasets against state-of-the-art baselines.

ICML Conference 2025 Conference Paper

Neural Interpretable PDEs: Harmonizing Fourier Insights with Attention for Scalable and Interpretable Physics Discovery

• Ning Liu
• Yue Yu

Attention mechanisms have emerged as transformative tools in core AI domains such as natural language processing and computer vision. Yet, their largely untapped potential for modeling intricate physical systems presents a compelling frontier. Learning such systems often entails discovering operators that map between functional spaces using limited instances of function pairs—a task commonly framed as a severely ill-posed inverse PDE problem. In this work, we introduce Neural Interpretable PDEs (NIPS), a novel neural operator architecture that builds upon and enhances Nonlocal Attention Operators (NAO) in both predictive accuracy and computational efficiency. NIPS employs a linear attention mechanism to enable scalable learning and integrates a learnable kernel network that acts as a channel-independent convolution in Fourier space. As a consequence, NIPS eliminates the need to explicitly compute and store large pairwise interactions, effectively amortizing the cost of handling spatial interactions into the Fourier transform. Empirical evaluations demonstrate that NIPS consistently surpasses NAO and other baselines across diverse benchmarks, heralding a substantial leap in scalable, interpretable, and efficient physics learning. Our code and data accompanying this paper are available at https: //github. com/fishmoon1234/Nonlocal-Attention-Operator.

EAAI Journal 2025 Journal Article

Nonlinear excavation load prediction of hydraulic excavator based on gated recurrent unit neural network

• Jinshi Chen
• Yue Yu
• Dongyang Huo
• Han Zhang
• Jingyan Wang

Excavator arms are integral to the mining and construction industries, where real-time excavation load prediction is a critical element for the advancement of automated excavation technology. This study presents a novel Physics-guided Neural Network (PGNN) designed to predict the excavating force of hydraulic cylinders used in earthwork excavation. The PGNN model synergizes the physical load model of excavators with a Gated Recurrent Unit (GRU) neural network and is optimized using the Hyperband algorithm to attain both high-speed and precise forecasting. Through comparative experiments, the study validates the PGNN model's ability to achieve optimal response speed and precision in predicting excavation loads. Additionally, the predictive performance of the PGNN model is assessed via a Hardware-in-the-loop (HIL) test, conducted within the context of an actual excavation experiment. This research introduces a promising approach that seamlessly integrates physics-based modeling with machine learning techniques, facilitating real-time load forecasting for excavators. The findings pave the way for more efficient and precise excavation processes, with implications for the broader fields of mining and construction automation.

EAAI Journal 2025 Journal Article

Retraction notice to “Optimal infrastructure in microgrids with diverse uncertainties based on demand response, renewable energy sources and two-stage parallel optimization algorithm” [Eng. Appl. Artif. Intell. 123 (2023) 106233]

• Yue Yu
• Laleh Shahabi

EAAI Journal 2025 Journal Article

SAFE-Net: Multi-head attention enhanced framework for defect detection in anti-corrosion coatings on steel structures

• Yue Yu
• Shouchao Jiang
• Yijun Wang
• Shaojun Zhu

Steel structures exhibit poor corrosion resistance and require anti-corrosion coatings for protection. Coating aging can lead to reduced or even ineffective anti-corrosion effects, so maintenance of their anti-corrosion coatings is crucial. Computer vision offers efficient and accurate analysis of visual data, but detecting defects in anti-corrosion coatings remains challenging due to low contrast, subtle background differences, varied defect types, image noise, and environmental interference. Existing networks often struggle to address these complexities effectively. In this context, this study proposes a You Only Look Once version 8 (YOLOv8)-driven SAFE-Net (Steel Anti Corruption Fault Evaluation Network) based on multiple attention mechanisms for detecting defects in anti-corrosion coatings on steel structures, and constructs a dataset for defect detection in in-service steel structure anti-corrosion coatings for model validation. The proposed framework integrates a multi-scale deformable attention mechanism into the Concatenate-to-Fuse module of the Backbone, aiming to improve the detection performance for small-scale targets. The Head adopts a Dynamic Head that integrates the self-attention mechanism to enhance scale perception, spatial perception, and task perception. The classification loss function is optimized by introducing the Slide Loss to address the challenge of imbalanced samples in the dataset, while Shape Intersection over Union refines the bounding box regression for better multi-scale detection. SAFE-Net supports multi-defect detection and demonstrates strong generalization. Numerical case studies indicate that, compared with the YOLOv8 baseline model, the improved algorithm improves the accuracy by 5. 82 %, recall by 5. 01 %, and mean Average Precision index by 4. 78 %, respectively.

UAI Conference 2025 Conference Paper

Sample and Computationally Efficient Continuous-Time Reinforcement Learning with General Function Approximation

• Runze Zhao
• Yue Yu
• Adams Yiyue Zhu
• Chen Yang
• Dongruo Zhou

Continuous-time reinforcement learning (CTRL) provides a principled framework for sequential decision-making in environments where interactions evolve continuously over time. Despite its empirical success, the theoretical understanding of CTRL remains limited, especially in settings with general function approximation. In this work, we propose a model-based CTRL algorithm that achieves both sample and computational efficiency. Our approach leverages optimism-based confidence sets to establish the first sample complexity guarantee for CTRL with general function approximation, showing that a near-optimal policy can be learned with a suboptimality gap of $\tilde{O}(\sqrt{d_{\mathcal{R}} + d_{\mathcal{F}}}N^{-1/2})$ using $N$ measurements, where $d_{\mathcal{R}}$ and $d_{\mathcal{F}}$ denote the distributional Eluder dimensions of the reward and dynamic functions, respectively, capturing the complexity of general function approximation in reinforcement learning. Moreover, we introduce structured policy updates and an alternative measurement strategy that significantly reduce the number of policy updates and rollouts while maintaining competitive sample efficiency. Our proposed algorithms are validated through experiments on continuous control tasks and diffusion model fine-tuning, demonstrating comparable performance with significantly fewer policy updates and rollouts.

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.

YNICL Journal 2024 Journal Article

Cortical morphological alterations in adolescents with major depression and non-suicidal self-injury

• Xiaonan Pang
• Dongpeng Wu
• Hongping Wang
• Jiahua Zhang
• Yue Yu
• Yue Zhao
• Qianqian Li
• Liangping Ni

BACKGROUND: Non-suicidal self-injury (NSSI) involves repetitive self-harm without suicidal intent and is common among adolescents, often linked to major depressive disorder (MDD). NSSI can lead to physical harm, cognitive impairments, interpersonal issues, violent behavior, and increased risks of psychological disorders and suicide attempts later in life. METHODS: Voxel-based morphometry (VBM) and surface-based morphometry (SBM) were performed on 44 NSSI patients and 44 healthy controls (HCs). Differences in GMV, CT, and cortical complexity were compared using the two-sample t-tests and correlated with neuropsychological scales. RESULTS: NSSI patients exhibited significant GMV atrophy in multiple regions, including the left insula, left anterior cingulate cortex, left putamen, left middle frontal gyrus, and right superior frontal gyrus showing increased GMV in the cerebellum posterior lobe. NSSI patients had increased CT in multiple left hemisphere regions and decreased CT in the right middle frontal gyrus. Additionally, they exhibited reduced cortical complexity, including decreased SD in the right frontal gyrus, and lower GI in the left insula. There were no significant differences between the two groups in terms of fractal dimension (FD). NSSI patients showed negative correlation between the CT of the right middle frontal gyrus and the anger dimension of the BPAQ, as well as the SD of the right superior frontal gyrus and the hostility dimension of the BPAQ. CONCLUSION: NSSI patients have significant structural changes in the insular cortex, prefrontal cortex, precentral and postcentral gyrus, temporal lobe, putamen, and anterior cingulate cortex, offering a morphological perspective on the pathophysiology of NSSI in MDD.

AAAI Conference 2024 Conference Paper

Effective Causal Discovery under Identifiable Heteroscedastic Noise Model

• Naiyu Yin
• Tian Gao
• Yue Yu
• Qiang Ji

Capturing the underlying structural causal relations represented by Directed Acyclic Graphs (DAGs) has been a fundamental task in various AI disciplines. Causal DAG learning via the continuous optimization framework has recently achieved promising performance in terms of accuracy and efficiency. However, most methods make strong assumptions of homoscedastic noise, i.e., exogenous noises have equal variances across variables, observations, or even both. The noises in real data usually violate both assumptions due to the biases introduced by different data collection processes. To address the heteroscedastic noise issue, we introduce relaxed implementable sufficient conditions and prove the identifiability of a general class of SEM subject to those conditions. Based on the identifiable general SEM, we propose a novel formulation for DAG learning which accounts for the noise variance variation across variables and observations. We then propose an effective two-phase iterative DAG learning algorithm to address the increasing optimization difficulties and learn a causal DAG from data with heteroscedastic variables noise under varying variance. We show significant empirical gains of the proposed approaches over state-of-the-art methods on both synthetic data and real data.

AAAI Conference 2024 Conference Paper

EncryIP: A Practical Encryption-Based Framework for Model Intellectual Property Protection

• Xin Mu
• Yu Wang
• Zhengan Huang
• Junzuo Lai
• Yehong Zhang
• Hui Wang
• Yue Yu

In the rapidly growing digital economy, protecting intellectual property (IP) associated with digital products has become increasingly important. Within this context, machine learning (ML) models, being highly valuable digital assets, have gained significant attention for IP protection. This paper introduces a practical encryption-based framework called EncryIP, which seamlessly integrates a public-key encryption scheme into the model learning process. This approach enables the protected model to generate randomized and confused labels, ensuring that only individuals with accurate secret keys, signifying authorized users, can decrypt and reveal authentic labels. Importantly, the proposed framework not only facilitates the protected model to multiple authorized users without requiring repetitive training of the original ML model with IP protection methods but also maintains the model's performance without compromising its accuracy. Compared to existing methods like watermark-based, trigger-based, and passport-based approaches, EncryIP demonstrates superior effectiveness in both training protected models and efficiently detecting the unauthorized spread of ML models.

ICML Conference 2024 Conference Paper

Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind

• Mo Yu
• Qiujing Wang
• Shunchi Zhang
• Yisi Sang
• Kangsheng Pu
• Zekai Wei
• Han Wang
• Liyan Xu

When reading a story, humans can quickly understand new fictional characters with a few observations, mainly by drawing analogies to fictional and real people they already know. This reflects the few-shot and meta-learning essence of humans’ inference of characters’ mental states, i. e. , theory-of-mind (ToM), which is largely ignored in existing research. We fill this gap with a novel NLP dataset in a realistic narrative understanding scenario, ToM-in-AMC. Our dataset consists of $\sim$1, 000 parsed movie scripts, each corresponding to a few-shot character understanding task that requires models to mimic humans’ ability of fast digesting characters with a few starting scenes in a new movie. We further propose a novel ToM prompting approach designed to explicitly assess the influence of multiple ToM dimensions. It surpasses existing baseline models, underscoring the significance of modeling multiple ToM dimensions for our task. Our extensive human study verifies that humans are capable of solving our problem by inferring characters’ mental states based on their previously seen movies. In comparison, all the AI systems lag $>20%$ behind humans, highlighting a notable limitation in existing approaches’ ToM capabilities. Code and data are available at https: //github. com/ShunchiZhang/ToM-in-AMC

NeurIPS Conference 2024 Conference Paper

HYDRA: Model Factorization Framework for Black-Box LLM Personalization

• Yuchen Zhuang
• Haotian Sun
• Yue Yu
• Rushi Qiang
• Qifan Wang
• Chao Zhang
• Bo Dai

Personalization has emerged as a critical research area in modern intelligent systems, focusing on mining users' behavioral history and adapting to their preferences for delivering tailored experiences. Despite the remarkable few-shot capabilities exhibited by black-box large language models (LLMs), the inherent opacity of their model parameters presents significant challenges in aligning the generated output with individual expectations. Existing solutions have primarily focused on prompt design to incorporate user-specific profiles and behaviors; however, such approaches often struggle to generalize effectively due to their inability to capture shared knowledge among all users. To address these challenges, we propose HYDRA, a model factorization framework that captures both user-specific behavior patterns from historical data and shared general knowledge among all users to deliver personalized generation. In order to capture user-specific behavior patterns, we first train a reranker to prioritize the most useful information from top-retrieved relevant historical records. By combining the prioritized history with the corresponding query, we train an adapter to align the output with individual user-specific preferences, eliminating the reliance on access to inherent model parameters of black-box LLMs. Both the reranker and the adapter can be decomposed into a base model with multiple user-specific heads, resembling a hydra. The base model maintains shared knowledge across users, while the multiple personal heads capture user-specific preferences. Experimental results demonstrate that \method outperforms existing state-of-the-art prompt-based methods by an average relative improvement of 9. 01% across five diverse personalization tasks in the LaMP benchmark.

ECAI Conference 2024 Conference Paper

Model Provenance via Model DNA

• Xin Mu
• Yu Wang
• Yehong Zhang
• Jiaqi Zhang
• Hui Wang
• Yang Xiang
• Yue Yu

Understanding the life cycle of the machine learning (ML) model is an intriguing area of research (e. g. , understanding where the model comes from, how it is trained, and how it is used). Our focus is on a novel problem within this domain, namely Model Provenance (MP). MP concerns the relationship between a target model and its pre-training model and aims to determine whether a source model serves as the provenance for a target model. In this paper, we formulate this new challenge as a learning problem, supplementing our exploration with empirical discussions on its connections to existing works. Following that, we introduce “Model DNA”, an interesting concept encoding the model’s training data and input-output information to create a compact machine-learning model representation. Capitalizing on this model DNA, we establish an efficient framework consisting of three key components: DNA generation, DNA similarity loss, and a provenance classifier, aimed at identifying model provenance. We conduct evaluations on both computer vision and natural language processing tasks using various models, datasets, and scenarios to demonstrate the effectiveness of our approach.

TMLR Journal 2024 Journal Article

MUBen: Benchmarking the Uncertainty of Molecular Representation Models

• Yinghao Li
• Lingkai Kong
• Yuanqi Du
• Yue Yu
• Yuchen Zhuang
• Wenhao Mu
• Chao Zhang

Large molecular representation models pre-trained on massive unlabeled data have shown great success in predicting molecular properties. However, these models may tend to overfit the fine-tuning data, resulting in over-confident predictions on test data that fall outside of the training distribution. To address this issue, uncertainty quantification (UQ) methods can be used to improve the models' calibration of predictions. Although many UQ approaches exist, not all of them lead to improved performance. While some studies have included UQ to improve molecular pre-trained models, the process of selecting suitable backbone and UQ methods for reliable molecular uncertainty estimation remains underexplored. To address this gap, we present MUBen, which evaluates different UQ methods for state-of-the-art backbone molecular representation models to investigate their capabilities. By fine-tuning various backbones using different molecular descriptors as inputs with UQ methods from different categories, we assess the influence of architectural decisions and training strategies on property prediction and uncertainty estimation. Our study offers insights for selecting UQ for backbone models, which can facilitate research on uncertainty-critical applications in fields such as materials science and drug discovery.

NeurIPS Conference 2024 Conference Paper

Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery

• Yue Yu
• Ning Liu
• Fei Lu
• Tian Gao
• Siavash Jafarzadeh
• Stewart Silling

Despite recent popularity of attention-based neural architectures in core AI fields like natural language processing (NLP) and computer vision (CV), their potential in modeling complex physical systems remains under-explored. Learning problems in physical systems are often characterized as discovering operators that map between function spaces based on a few instances of function pairs. This task frequently presents a severely ill-posed PDE inverse problem. In this work, we propose a novel neural operator architecture based on the attention mechanism, which we coin Nonlocal Attention Operator (NAO), and explore its capability towards developing a foundation physical model. In particular, we show that the attention mechanism is equivalent to a double integral operator that enables nonlocal interactions among spatial tokens, with a data-dependent kernel characterizing the inverse mapping from data to the hidden parameter field of the underlying operator. As such, the attention mechanism extracts global prior information from training data generated by multiple systems, and suggests the exploratory space in the form of a nonlinear kernel map. Consequently, NAO can address ill-posedness and rank deficiency in inverse PDE problems by encoding regularization and achieving generalizability. Lastly, we empirically demonstrate the advantages of NAO over baseline neural models in terms of the generalizability to unseen data resolutions and system states. Our work not only suggests a novel neural operator architecture for learning an interpretable foundation model of physical systems, but also offers a new perspective towards understanding the attention mechanism.

NeurIPS Conference 2024 Conference Paper

RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMs

• Yue Yu
• Wei Ping
• Zihan Liu
• Boxin Wang
• Jiaxuan You
• Chao Zhang
• Mohammad Shoeybi
• Bryan Catanzaro

Large language models (LLMs) typically utilize the top-k contexts from a retriever in retrieval-augmented generation (RAG). In this work, we propose a novel method called RankRAG, which instruction-tunes a single LLM for both context ranking and answer generation in RAG. In particular, the instruction-tuned LLMs work surprisingly well by adding a small fraction of ranking data into the training blend, and outperform existing expert ranking models, including the same LLM exclusively fine-tuned on a large amount of ranking data. For generation, we compare our model with many strong baselines, including ChatQA-1. 5, an open-sourced model with the state-of-the-art performance on RAG benchmarks. Specifically, our Llama3-RankRAG-8B and Llama3-RankRAG-70B significantly outperform Llama3-ChatQA-1. 5-8B and Llama3-ChatQA-1. 5-70B, respectively, on nine general knowledge-intensive benchmarks for RAG. In addition, it also performs comparably to GPT-4 on five RAG benchmarks in the biomedical domain without instruction fine-tuning on biomedical data, demonstrating its superb capability for generalization to new domains.

AAAI Conference 2024 Conference Paper

Towards Fair Graph Federated Learning via Incentive Mechanisms

• Chenglu Pan
• Jiarong Xu
• Yue Yu
• Ziqi Yang
• Qingbiao Wu
• Chunping Wang
• Lei Chen
• Yang Yang

Graph federated learning (FL) has emerged as a pivotal paradigm enabling multiple agents to collaboratively train a graph model while preserving local data privacy. Yet, current efforts overlook a key issue: agents are self-interested and would hesitant to share data without fair and satisfactory incentives. This paper is the first endeavor to address this issue by studying the incentive mechanism for graph federated learning. We identify a unique phenomenon in graph federated learning: the presence of agents posing potential harm to the federation and agents contributing with delays. This stands in contrast to previous FL incentive mechanisms that assume all agents contribute positively and in a timely manner. In view of this, this paper presents a novel incentive mechanism tailored for fair graph federated learning, integrating incentives derived from both model gradient and payoff. To achieve this, we first introduce an agent valuation function aimed at quantifying agent contributions through the introduction of two criteria: gradient alignment and graph diversity. Moreover, due to the high heterogeneity in graph federated learning, striking a balance between accuracy and fairness becomes particularly crucial. We introduce motif prototypes to enhance accuracy, communicated between the server and agents, enhancing global model aggregation and aiding agents in local model optimization. Extensive experiments show that our model achieves the best trade-off between accuracy and the fairness of model gradient, as well as superior payoff fairness.

NeurIPS Conference 2023 Conference Paper

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

• Hanyang Peng
• Shuang Qin
• Yue Yu
• Jin Wang
• Hui Wang
• Ge Li

Various gradient compression algorithms have been proposed to alleviate the communication bottleneck in distributed learning, and they have demonstrated effectiveness in terms of high compression ratios and theoretical low communication complexity. However, when it comes to practically training modern deep neural networks (DNNs), these algorithms have yet to match the inference performance of uncompressed SGD-momentum (SGDM) and adaptive optimizers (e. g. ,Adam). More importantly, recent studies suggest that these algorithms actually offer no speed advantages over SGDM/Adam when used with common distributed DNN training frameworks ( e. g. , DistributedDataParallel (DDP)) in the typical settings, due to heavy compression/decompression computation or incompatibility with the efficient All-Reduce or the requirement of uncompressed warmup at the early stage. For these reasons, we propose a novel 1-bit adaptive optimizer, dubbed *Bi*nary *r*andomization a*d*aptive optimiz*er* (**Birder**). The quantization of Birder can be easily and lightly computed, and it does not require warmup with its uncompressed version in the beginning. Also, we devise Hierarchical-1-bit-All-Reduce to further lower the communication volume. We theoretically prove that it promises the same convergence rate as the Adam. Extensive experiments, conducted on 8 to 64 GPUs (1 to 8 nodes) using DDP, demonstrate that Birder achieves comparable inference performance to uncompressed SGDM/Adam, with up to ${2. 5 \times}$ speedup for training ResNet-50 and ${6. 3\times}$ speedup for training BERT-Base. Code is publicly available at https: //openi. pcl. ac. cn/c2net_optim/Birder.

JBHI Journal 2023 Journal Article

CUSS-Net: A Cascaded Unsupervised-Based Strategy and Supervised Network for Biomedical Image Diagnosis and Segmentation

• Xiaogen Zhou
• Zhiqiang Li
• Yuyang Xue
• Shun Chen
• Meijuan Zheng
• Cong Chen
• Yue Yu
• Xingqing Nie

Biomedical image segmentation and classification are critical components in a computer-aided diagnosis system. However, various deep convolutional neural networks are trained by a single task, ignoring the potential contribution of mutually performing multiple tasks. In this paper, we propose a cascaded unsupervised-based strategy to boost the supervised CNN framework for automated white blood cell (WBC) and skin lesion segmentation and classification, called CUSS-Net. Our proposed CUSS-Net consists of an unsupervised-based strategy (US) module, an enhanced segmentation network named E-SegNet, and a mask-guided classification network called MG-ClsNet. On the one hand, the proposed US module produces coarse masks that provide a prior localization map for the proposed E-SegNet to enhance it in locating and segmenting a target object accurately. On the other hand, the enhanced coarse masks predicted by the proposed E-SegNet are then fed into the proposed MG-ClsNet for accurate classification. Moreover, a novel cascaded dense inception module is presented to capture more high-level information. Meanwhile, we adopt a hybrid loss by combining a dice loss and a cross-entropy loss to alleviate the imbalance training problem. We evaluate our proposed CUSS-Net on three public medical image datasets. Experiments show that our proposed CUSS-Net outperforms representative state-of-the-art approaches.

NeurIPS Conference 2023 Conference Paper

Domain Agnostic Fourier Neural Operators

• Ning Liu
• Siavash Jafarzadeh
• Yue Yu

Fourier neural operators (FNOs) can learn highly nonlinear mappings between function spaces, and have recently become a popular tool for learning responses of complex physical systems. However, to achieve good accuracy and efficiency, FNOs rely on the Fast Fourier transform (FFT), which is restricted to modeling problems on rectangular domains. To lift such a restriction and permit FFT on irregular geometries as well as topology changes, we introduce domain agnostic Fourier neural operator (DAFNO), a novel neural operator architecture for learning surrogates with irregular geometries and evolving domains. The key idea is to incorporate a smoothed characteristic function in the integral layer architecture of FNOs, and leverage FFT to achieve rapid computations, in such a way that the geometric information is explicitly encoded in the architecture. In our empirical evaluation, DAFNO has achieved state-of-the-art accuracy as compared to baseline neural operator models on two benchmark datasets of material modeling and airfoil simulation. To further demonstrate the capability and generalizability of DAFNO in handling complex domains with topology changes, we consider a brittle material fracture evolution problem. With only one training crack simulation sample, DAFNO has achieved generalizability to unseen loading scenarios and substantially different crack patterns from the trained scenario. Our code and data accompanying this paper are available at https: //github. com/ningliu-iga/DAFNO.

NeurIPS Conference 2023 Conference Paper

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

• Yue Yu
• Yuchen Zhuang
• Jieyu Zhang
• Yu Meng
• Alexander J. Ratner
• Ranjay Krishna
• Jiaming Shen
• Chao Zhang

Large language models (LLMs) have been recently leveraged as training data generators for various natural language processing (NLP) tasks. While previous research has explored different approaches to training models using generated data, they generally rely on simple class-conditional prompts, which may limit the diversity of the generated data and inherit systematic biases of LLM. Thus, we investigate training data generation with diversely attributed prompts (e. g. , specifying attributes like length and style), which have the potential to yield diverse and attributed generated data. Our investigation focuses on datasets with high cardinality and diverse domains, wherein we demonstrate that attributed prompts outperform simple class-conditional prompts in terms of the resulting model's performance. Additionally, we present a comprehensive empirical study on data generation encompassing vital aspects like bias, diversity, and efficiency, and highlight three key observations: firstly, synthetic datasets generated by simple prompts exhibit significant biases, such as regional bias; secondly, attribute diversity plays a pivotal role in enhancing model performance; lastly, attributed prompts achieve the performance of simple class-conditional prompts while utilizing only 5\% of the querying cost of ChatGPT associated with the latter. The data and code are available on {\url{https: //github. com/yueyu1030/AttrPrompt}}.

AAAI Conference 2023 Conference Paper

Neighborhood-Regularized Self-Training for Learning with Few Labels

• Ran Xu
• Yue Yu
• Hejie Cui
• Xuan Kan
• Yanqiao Zhu
• Joyce Ho
• Chao Zhang
• Carl Yang

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one drawback of self-training is that it is vulnerable to the label noise from incorrect pseudo labels. Inspired by the fact that samples with similar labels tend to share similar representations, we develop a neighborhood-based sample selection approach to tackle the issue of noisy pseudo labels. We further stabilize self-training via aggregating the predictions from different rounds during sample selection. Experiments on eight tasks show that our proposed method outperforms the strongest self-training baseline with 1.83% and 2.51% performance gain for text and graph datasets on average. Our further analysis demonstrates that our proposed data selection strategy reduces the noise of pseudo labels by 36.8% and saves 57.3% of the time when compared with the best baseline. Our code and appendices will be uploaded to: https://github.com/ritaranx/NeST.

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.

NeurIPS Conference 2023 Conference Paper

Provable Training for Graph Contrastive Learning

• Yue Yu
• Xiao Wang
• Mengmei Zhang
• Nian Liu
• Chuan Shi

Graph Contrastive Learning (GCL) has emerged as a popular training approach for learning node embeddings from augmented graphs without labels. Despite the key principle that maximizing the similarity between positive node pairs while minimizing it between negative node pairs is well established, some fundamental problems are still unclear. Considering the complex graph structure, are some nodes consistently well-trained and following this principle even with different graph augmentations? Or are there some nodes more likely to be untrained across graph augmentations and violate the principle? How to distinguish these nodes and further guide the training of GCL? To answer these questions, we first present experimental evidence showing that the training of GCL is indeed imbalanced across all nodes. To address this problem, we propose the metric "node compactness", which is the lower bound of how a node follows the GCL principle related to the range of augmentations. We further derive the form of node compactness theoretically through bound propagation, which can be integrated into binary cross-entropy as a regularization. To this end, we propose the PrOvable Training (POT) for GCL, which regularizes the training of GCL to encode node embeddings that follows the GCL principle better. Through extensive experiments on various benchmarks, POT consistently improves the existing GCL approaches, serving as a friendly plugin.

EAAI Journal 2023 Journal Article

RETRACTED: Optimal infrastructure in microgrids with diverse uncertainties based on demand response, renewable energy sources and two-stage parallel optimization algorithm

• Yue Yu
• Laleh Shahabi

This article has been retracted: please see Elsevier Policy on Article Withdrawal (https: //www. elsevier. com/locate/withdrawalpolicy). This article has been retracted at the request of the Editor-in-Chief. Post-publication, the editors discovered suspicious changes in authorship between the original submission and the revised version of this paper. In summary, the paper was submitted by a sole author, Laleh Shahabi. During revision, the author name Yue Yu was added to the revised paper (as a new First and Corresponding Author) without explanation and without exceptional approval by the journal editor, which is contrary to the journal policy on changes to authorship. The editors reached out to the authors for an explanation, but they failed to provide a satisfactory explanation to these changes. In addition, it appears that Laleh Shahabi was claiming an affiliation with Sun-life Company, Baku, Azerbaijan. When questioned, the author was unable to provide convincing evidence of the existence and nature of this company. Overall, the editors feels that the findings of the manuscript cannot be relied upon and that the article needs to be retracted.

NeurIPS Conference 2023 Conference Paper

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

• Alexander Bukharin
• Yan Li
• Yue Yu
• Qingru Zhang
• Zhehui Chen
• Simiao Zuo
• Chao Zhang
• Songan Zhang

Multi-Agent Reinforcement Learning (MARL) has shown promising results across several domains. Despite this promise, MARL policies often lack robustness and are therefore sensitive to small changes in their environment. This presents a serious concern for the real world deployment of MARL algorithms, where the testing environment may slightly differ from the training environment. In this work we show that we can gain robustness by controlling a policy’s Lipschitz constant, and under mild conditions, establish the existence of a Lipschitz and close-to-optimal policy. Motivated by these insights, we propose a new robust MARL framework, ERNIE, that promotes the Lipschitz continuity of the policies with respect to the state observations and actions by adversarial regularization. The ERNIE framework provides robustness against noisy observations, changing transition dynamics, and malicious actions of agents. However, ERNIE’s adversarial regularization may introduce some training instability. To reduce this instability, we reformulate adversarial regularization as a Stackelberg game. We demonstrate the effectiveness of the proposed framework with extensive experiments in traffic light control and particle environments. In addition, we extend ERNIE to mean-field MARL with a formulation based on distributionally robust optimization that outperforms its non-robust counterpart and is of independent interest. Our code is available at https: //github. com/abukharin3/ERNIE.

NeurIPS Conference 2023 Conference Paper

ToolQA: A Dataset for LLM Question Answering with External Tools

• Yuchen Zhuang
• Yue Yu
• Kuan Wang
• Haotian Sun
• Chao Zhang

Large Language Models (LLMs) have demonstrated impressive performance in various NLP tasks, but they still suffer from challenges such as hallucination and weak numerical reasoning. To overcome these challenges, external tools can be used to enhance LLMs' question-answering abilities. However, current evaluation methods do not distinguish between questions that can be answered using LLMs' internal knowledge and those that require external information through tool use. To address this issue, we introduce a new dataset called ToolQA, which is designed to faithfully evaluate LLMs' ability to use external tools for question answering. Our development of ToolQA involved a scalable, automated process for dataset curation, along with 13 specialized tools designed for interaction with external knowledge in order to answer questions. Importantly, we strive to minimize the overlap between our benchmark data and LLMs' pre-training data, enabling a more precise evaluation of LLMs' tool-use reasoning abilities. We conducted an in-depth diagnosis of existing tool-use LLMs to highlight their strengths, weaknesses, and potential improvements. Our findings set a new benchmark for evaluating LLMs and suggest new directions for future advancements. Our data and code are freely available for the broader scientific community on GitHub.

NeurIPS Conference 2021 Conference Paper

WRENCH: A Comprehensive Benchmark for Weak Supervision

• Jieyu Zhang
• Yue Yu
• Yujing Wang
• Yaming Yang
• Mao Yang
• Alexander Ratner

Recent Weak Supervision (WS) approaches have had widespread success in easing the bottleneck of labeling training data for machine learning by synthesizing labels from multiple potentially noisy supervision sources. However, proper measurement and analysis of these approaches remain a challenge. First, datasets used in existing works are often private and/or custom, limiting standardization. Second, WS datasets with the same name and base data often vary in terms of the labels and weak supervision sources used, a significant "hidden" source of evaluation variance. Finally, WS studies often diverge in terms of the evaluation protocol and ablations used. To address these problems, we introduce a benchmark platform, WRENCH, for thorough and standardized evaluation of WS approaches. It consists of 22 varied real-world datasets for classification and sequence tagging; a range of real, synthetic, and procedurally-generated weak supervision sources; and a modular, extensible framework for WS evaluation, including implementations for popular WS methods. We use WRENCH to conduct extensive comparisons over more than 120 method variants to demonstrate its efficacy as a benchmark platform. The code is available at https: //github. com/JieyuZ2/wrench.

NeurIPS Conference 2020 Conference Paper

DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks

• Dennis Wei
• Tian Gao
• Yue Yu

This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks. We first generalize existing algebraic characterizations of acyclicity to a class of matrix polynomials. Next, focusing on a one-parameter-per-edge setting, it is shown that the Karush-Kuhn-Tucker (KKT) optimality conditions for the NOTEARS formulation cannot be satisfied except in a trivial case, which explains a behavior of the associated algorithm. We then derive the KKT conditions for an equivalent reformulation, show that they are indeed necessary, and relate them to explicit constraints that certain edges be absent from the graph. If the score function is convex, these KKT conditions are also sufficient for local minimality despite the non-convexity of the constraint. Informed by the KKT conditions, a local search post-processing algorithm is proposed and shown to substantially and universally improve the structural Hamming distance of all tested algorithms, typically by a factor of 2 or more. Some combinations with local search are both more accurate and more efficient than the original NOTEARS.

NeurIPS Conference 2019 Conference Paper

Double Quantization for Communication-Efficient Distributed Optimization

• Yue Yu
• Jiaxiang Wu
• Longbo Huang

Modern distributed training of machine learning models often suffers from high communication overhead for synchronizing stochastic gradients and model parameters. In this paper, to reduce the communication complexity, we propose \emph{double quantization}, a general scheme for quantizing both model parameters and gradients. Three communication-efficient algorithms are proposed based on this general scheme. Specifically, (i) we propose a low-precision algorithm AsyLPG with asynchronous parallelism, (ii) we explore integrating gradient sparsification with double quantization and develop Sparse-AsyLPG, (iii) we show that double quantization can be accelerated by the momentum technique and design accelerated AsyLPG. We establish rigorous performance guarantees for the algorithms, and conduct experiments on a multi-server test-bed with real-world datasets to demonstrate that our algorithms can effectively save transmitted bits without performance degradation, and significantly outperform existing methods with either model parameter or gradient quantization.

IROS Conference 2019 Conference Paper

Robust Loop Closure Detection based on Bag of SuperPoints and Graph Verification

• Haosong Yue
• Jinyu Miao
• Yue Yu
• Weihai Chen
• Changyun Wen

Loop closure detection (LCD) is a crucial technique for robots, which can correct accumulated localization errors after long time explorations. In this paper, we propose a robust LCD algorithm based on Bag of SuperPoints and graph verification. The system first extracts interest points and feature descriptors using the SuperPoint neural network. Then a visual vocabulary is trained in an incremental and self-supervised manner considering the relations between consecutive training images. Finally, a topological graph is constructed using matched feature points to verify candidate loop closures obtained by a Bag-of-Words (BoW) framework. Comparative experiments with state-of-the-art LCD algorithms on several typical datasets have been carried out. The results demonstrate that our proposed graph verification method can significantly improve the accuracy of image matching and the overall LCD approach outperforms existing methods.

IJCAI Conference 2017 Conference Paper

Fast Stochastic Variance Reduced ADMM for Stochastic Composition Optimization

• Yue Yu
• Longbo Huang

We consider the stochastic composition optimization problem proposed in \cite{wang2017stochastic}, which has applications ranging from estimation to statistical and machine learning. We propose the first ADMM based algorithm named com SVR ADMM, and show that com SVR ADMM converges linearly for strongly convex and Lipschitz smooth objectives, and has a convergence rate of $O(\logS/S)$, which improves upon the $O(S^{-4/9})$ rate in \cite{wang2016accelerating} when the objective is convex and Lipschitz smooth. Moreover, com SVR ADMM possesses a rate of $O(1/\sqrt{S})$ when the objective is convex but without Lipschitz smoothness. We also conduct experiments and show that it outperforms existing algorithms.

IJCAI Conference 2016 Conference Paper

Decision-Making Policies for Heterogeneous Autonomous Multi-Agent Systems with Safety Constraints

• Ruohan Zhang
• Yue Yu
• Mahmoud El Chamie
• Beh
• ccedil; et A
• ccedil; ıkmese
• Dana H. Ballard

This paper studies a decision-making problem for heterogeneous multi-agent systems with safety density constraints. An individual agent's decision-making problem is modeled by the standard Markov Decision Process (MDP) formulation. However, an important special case occurs when the MDP states may have limited capacities, hence upper bounds on the expected number of agents in each state are imposed. We refer to these upper bound constraints as "safety" constraints. If agents follow unconstrained policies (policies that do not impose the safety constraints), the safety constraints might be violated. In this paper, we devise algorithms that provide safe decision-making policies. The set of safe decision policies can be shown to be convex, and hence the policy synthesis is tractable via reliable and fast Interior Point Method (IPM) algorithms. We evaluate the effectiveness of proposed algorithms first using a simple MDP, and then using a dynamic traffic assignment problem. The numerical results demonstrate that safe decision-making algorithms in this paper significantly outperform other baselines.

TAAS Journal 2007 Journal Article

The role of roles in supporting reconfigurability and fault localizations for open distributed and embedded systems

• Shangping Ren
• Yue Yu
• Nianen Chen
• Jeffrey J.-P. Tsai
• Kevin Kwiat

One of the main characteristics of open distributed embedded systems is that the involved entities are often very dynamic—different individual entities may join or leave the systems frequently. Therefore, systems built of these dynamic entities must be runtime reconfigurable. In addition, large classes of open embedded systems often have high availability and dependability requirements. However, the openness makes these requirements more difficult to achieve and the system more vulnerable to attacks. This article presents a coordination model, the Actor, Role and Coordinator (ARC) model, that aims to support reconfigurability and fault localization for open distributed embedded software systems. In particular, the actor model is used to model concurrent embedded entities, while the system's reconfigurability and dependability requirements are encapsulated within coordination objects: roles and coordinators, and are achieved through coordination among the actors. Roles, as a key thrust in the ARC model not only represent an abstraction for a set of behaviors shared by a group of actors so that reconfiguration within the roles becomes transparent to entities outside the roles, but also assume coordination responsibilities among the member actors. The article also argues from both analytical and empirical perspectives that with the support of the role, faults can be localized within actors, and actor level reconfiguration becomes transparent to the system.