Author name cluster

Jianwei Yin

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.

35 papers

2 author rows

AAAI Conference 2026 Conference Paper

Adaptive Fidelity Estimation for Quantum Programs with Graph-Guided Noise Awareness

Tingting Li
Ziming Zhao
Jianwei Yin

Fidelity estimation is a critical yet resource-intensive step in testing quantum programs on noisy intermediate-scale quantum (NISQ) devices, where the required number of measurements is difficult to predefine due to hardware noise, device heterogeneity, and transpilation-induced circuit transformations. We present QuFid, an adaptive and noise-aware framework that determines measurement budgets online by leveraging circuit structure and runtime statistical feedback. QuFid models a quantum program as a directed acyclic graph (DAG) and employs a control-flow-aware random walk to characterize noise propagation along gate dependencies. Backend-specific effects are captured via transpilation-induced structural deformation metrics, which are integrated into the random-walk formulation to induce a noise-propagation operator. Circuit complexity is then quantified through the spectral characteristics of this operator, providing a principled and lightweight basis for adaptive measurement planning. Experiments on 18 quantum benchmarks executed on IBM Quantum backends show that QuFid significantly reduces measurement cost compared to fixed-shot and learning-based baselines, while consistently maintaining acceptable fidelity bias.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Ground What You See: Hallucination-Resistant MLLMs via Caption Feedback, Diversity-Aware Sampling, and Conflict Regularization

Miao Pan
Wangjie Gan
Jintao Chen
Wenqi Zhang
Sun Bing
Jianwei Yin
Xuhong Zhang

Multimodal large language models (MLLMs) have achieved significant results in various tasks, but their practical application is still severely constrained by hallucination issues, which are particularly prominent in reinforcement learning (RL) optimization processes. This paper systematically analyzes the causes of hallucinations in MLLM under RL training, identifying three key factors: (1) The model relies heavily on chained visual reasoning to guide decision-making during RL training. Thus, error and irrelevant information in visual reasoning can easily cause hallucinations, including inaccurate initial visual descriptions that anchor subsequent inferences to incorrect information, as well as redundant and broad inferential information; (2) Insufficient exploration diversity during the policy optimization phase, causing the model to output overly confident results; (3) The destructive conflict between different samples during optimization is a key factor that leads to false associations and unstable parameter updates. To address these issues, we propose a solution framework comprising three core modules. First, to improve the accuracy of visual localization, we add planning and caption stages before thinking and answer stages. To enhance initial visual descriptions ability, we allow LLMs to respond based solely on the caption and provide corresponding caption reward based on the quality of the response. Second, to enhance exploration capabilities, we classify samples based on the mean and variance of the reward distribution and select samples with high reward variance for training, thereby increasing the model's focus on diverse samples. Finally, to mitigate conflicts between training samples, we identify neural tangent kernel (NTK) similarity as the key factor. Rather than minimizing it uniformly, we regulate NTK similarity by grouping sample pairs based on a similarity threshold. An InfoNCE loss is then applied to pull dissimilar pairs closer and push overly similar ones apart, guiding interactions toward a balanced range. The experimental results demonstrate that the proposed method significantly reduces the hallucination rate and effectively improves the inference accuracy of MLLMs.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Relational Verification for Cost-Aware Quantum Program Optimization

Ziming Zhao
Tingting Li
Zhaoxuan Li
Jianwei Yin

Optimizing quantum programs is key to mitigating noise, reducing error-correction overhead, and improving performance on both near-term and fault-tolerant devices. Existing heuristic and learning-based optimizers, however, lack formal guarantees and risk semantic errors in the presence of entanglement and measurement. We present RelOpt, a semantics-preserving optimizer that enforces relational correctness between original and optimized programs. RelOpt is built on a lightweight intermediate language (QCore) with a relational operational semantics supporting partial-trace equivalence, measurement-distribution preservation, and approximate correctness. Optimization is guided by a multi-objective cost model that considers gate count, circuit depth, and error-correction cost. Only rewrite rules that are formally verified against user-specified contracts are applied. The engine combines symbolic simulation, SMT reasoning, and cost analysis to achieve safe and effective optimizations. On standard benchmarks such as QFT, Grover, and QAOA, RelOpt consistently outperforms Qiskit, t|ket>, and learning-based optimizers across multiple cost metrics while maintaining formal guarantees. By integrating formal verification with cost-aware compilation, RelOpt establishes a foundation for trustworthy and hardware-adaptive quantum toolchains.

PDF Details DOI

I&C Journal 2026 Journal Article

Truthful approximation for rank-maximal matchings

Jinshan Zhang
Hao Xu
Feng Wang
Meng Xi
Xiaotie Deng
Jianwei Yin

In this work, we investigate truthful mechanisms for the rank-maximal matching problem from an approximation standpoint. Our findings narrow the gap between the upper and lower bounds. We introduce a lexicographically truthful (LT) and nearly Pareto optimal (PO) randomized mechanism with an approximation ratio of 2 e − 1 2 e − 2 ≈ 1. 77, an improvement over the previous best result of 2. Key to our algorithm are preservation lemmas that enable us to leverage techniques from online algorithms to analyze the new approximation ratio. Furthermore, we present several hardness results across different settings to enhance our upper bound. Notably, we improve the lower bound for the approximation ratio of our LT and PO mechanism to 18 / 13 ≈ 1. 38. To our knowledge, this is the first instance of a lower bound being established using a linear programming approach in this field.

Details DOI

TAAS Journal 2025 Journal Article

Adaptive Scheduling of High-Availability Drone Swarms for Congestion Alleviation in Connected Automated Vehicles

Shengye Pang
Yi Li
Zhen Qin
Xinkui Zhao
Jintao Chen
Fan Wang
Jianwei Yin

The Intelligent Transportation System (ITS) serves as a pivotal element within urban networks, offering decision support to users and connected automated vehicles through comprehensive information gathering, sensing, device control, and data processing. Presently, ITS predominantly relies on sensors embedded in fixed infrastructure, notably Roadside Units (RSUs). However, RSUs are confined by coverage limitations and may encounter challenges in prompt emergency responses. On-demand resources, such as drones, present a viable option to supplement these deficiencies effectively. This article introduces an approach where Software-Defined Networking and Mobile Edge Computing technologies are integrated to formulate a high-availability drone swarm control and communication infrastructure framework comprising the cloud layer, edge layer, and device layer. Drones confront limitations in flight duration attributed to battery limitations, posing a challenge in sustaining continuous monitoring of road conditions over extended periods. Effective drone scheduling stands as a promising solution to overcome these constraints. To tackle this issue, we initially utilized Graph WaveNet, a specialized graph neural network structure tailored for spatial-temporal graph modeling, for training a congestion prediction model using real-world dataset inputs. Building upon this, we further propose an algorithm for drone scheduling based on congestion prediction. Our simulation experiments using real-world data demonstrate that, compared to the baseline method, the proposed scheduling algorithm not only yielded superior scheduling gains but also mitigated drone idle rates.

Details DOI

ICLR Conference 2025 Conference Paper

Bridging Context Gaps: Leveraging Coreference Resolution for Long Contextual Understanding

Yanming Liu 0003
Xinyue Peng
Jiannan Cao
Shi Bo
Yanxin Shen
Tianyu Du
Sheng Cheng
Xun Wang

Large language models (LLMs) have shown remarkable capabilities in natural language processing; however, they still face difficulties when tasked with understanding lengthy contexts and executing effective question answering. These challenges often arise due to the complexity and ambiguity present in longer texts. To enhance the performance of LLMs in such scenarios, we introduce the Long Question Coreference Adaptation (LQCA) method. This innovative framework focuses on coreference resolution tailored to long contexts, allowing the model to identify and manage references effectively. The LQCA method encompasses four key steps: resolving coreferences within sub-documents, computing the distances between mentions, defining a representative mention for coreference, and answering questions through mention replacement. By processing information systematically, the framework provides easier-to-handle partitions for LLMs, promoting better understanding. Experimental evaluations on a range of LLMs and datasets have yielded positive results, with a notable improvements on OpenAI-o1-mini and GPT-4o models, highlighting the effectiveness of leveraging coreference resolution to bridge context gaps in question answering. Our code is public at https://github.com/OceannTwT/LQCA.

Details

ICLR Conference 2025 Conference Paper

CollabEdit: Towards Non-destructive Collaborative Knowledge Editing

Jiamu Zheng
Jinghuai Zhang
Tianyu Du
Xuhong Zhang 0002
Jianwei Yin
Tao Lin

Collaborative learning of large language models (LLMs) has emerged as a new paradigm for utilizing private data from different parties to guarantee efﬁciency and privacy. Meanwhile, Knowledge Editing (KE) for LLMs has also garnered increased attention due to its ability to manipulate the behaviors of LLMs explicitly, yet leaves the collaborative KE case—in which knowledge edits of multiple parties are aggregated in a privacy-preserving and continual manner—unexamined. To this end, this manuscript dives into the ﬁrst investigation of collaborative KE, in which we start by carefully identifying the unique three challenges therein, including knowledge overlap, knowledge conﬂict, and knowledge forgetting. We then propose a non-destructive collaborative KE framework, COLLABEDIT, which employs a novel model merging mechanism to mimic the global KE behavior while preventing the severe performance drop. Extensive experiments on two canonical datasets demonstrate the superiority of COLLABEDIT compared to other destructive baselines, and results shed light on addressing three collaborative KE challenges and future applications. Our code is available at [https://github.com/LINs-lab/CollabEdit](https://github.com/LINs-lab/CollabEdit).

Details

NeurIPS Conference 2025 Conference Paper

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Qinfeng Li
Tianyue Luo
Xuhong Zhang
Yangfan Xie
Zhiqiang Shen
Lijun Zhang
Yier Jin
Hao Peng

Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge devices for efficiency and privacy reasons. However, deploying proprietary LLMs at the edge without adequate protection introduces critical security threats. Attackers can extract model weights and architectures, enabling unauthorized copying and misuse. Even when protective measures prevent full extraction of model weights, attackers may still perform advanced attacks, such as fine-tuning, to further exploit the model. Existing defenses against these threats typically incur significant computational and communication overhead, making them impractical for edge deployment. To safeguard the edge-deployed LLMs, we introduce CoreGuard, a computation- and communication-efficient protection method. CoreGuard employs an efficient protection protocol to reduce computational overhead and minimize communication overhead via a propagation protocol. Extensive experiments show that CoreGuard achieves upper-bound security protection with negligible overhead.

PDF Details

AAAI Conference 2025 Conference Paper

DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models

Yanming Liu
Xinyue Peng
Yuwei Zhang
Xiaolan Ke
Songhang Deng
Jiannan Cao
Chen Ma
Mengchen Fu

Large language models have repeatedly shown outstanding performance across diverse applications. However, deploying these models can inadvertently risk user privacy. The significant memory demands during training pose a major challenge in terms of resource consumption. This substantial size places a heavy load on memory resources, raising considerable practical concerns. In this paper, we introduce DP-MemArc, a novel training framework aimed at reducing the memory costs of large language models while emphasizing the protection of user data privacy. DP-MemArc incorporates side network or reversible network designs to support a variety of differential privacy memory-efficient fine-tuning schemes. Our approach not only achieves about 2.5 times in memory optimization but also ensures robust privacy protection, keeping user data secure and confidential. Extensive experiments have demonstrated that DP-MemArc effectively provides differential privacy-efficient fine-tuning across different task scenarios.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DR-VAE: Debiased and Representation-enhanced Variational Autoencoder for Collaborative Recommendation

Fan Wang
Chaochao Chen
Weiming Liu
Minye Lei
Jintao Chen
Yuwen Liu
Xiaolin Zheng
Jianwei Yin

Recommender Systems (RSs) are widely applied for navigating information, and Collaborative Filtering (CF) is one of prominent recommendation techniques due to the advantages of domain independence and easy interpretation. Among the numerous CF methods, Variational Autoencoders (VAE), benefiting from modeling in a probabilitistic way, stands out in capturing user preferences through representation learning. Despite the superiority, VAE-based CF models still suffer from two challenging problems: (1) Exposure bias: models in training state are narrowly exposed to a limited, biased sample of data, leading to a skewed understanding of users' true preferences; (2) Posterior collapse: models excessively simplify the learned latent variable distributions, generating na"ive representations that are unable to encapsulate the complex data patterns and thereby resulting improper recommendations. In this paper, we propose a Debiased and Representation-enhanced Variational AutoEncoder (DR-VAE) framework for collaborative recommendations. Specifically, for exposure bias problem, DR-VAE incorporates a Debiasing Estimator, mitigating the impact of exposure bias. For poster collapse issue, DR-VAE innovatively introduces a Flow-based Representation Enhancement module, ensuring us to encapsulate complex data patterns by fitting complex and intricate posterior distributions directly. We provide experimental validations over four datasets to substantiate the efficacy of our DR-VAE framework.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Empowering Quantum Serverless Circuit Deployment Optimization via Graph Contrastive Learning and Learning-to-Rank Co-designed Approaches

Tingting Li
Ziming Zhao
Jianwei Yin

With the rapid advancements in quantum computing, cloud-based quantum services have gained increasing prominence. However, due to quantum noise, optimizing the deployment of quantum circuits remains an NP-hard problem with an expansive search space. Existing methods usually use heuristic algorithms to approximate the solution, such as the representative IBM Qiskit. On the one hand, they often find suboptimal deployment solutions. On the other hand, prior technologies do not consider user-specific requirements and can only provide a single deployment strategy. In this paper, we propose QCDeploy that can provide a ranked list of effective deployment strategies to optimize quantum serverless circuit deployment. Specifically, we model quantum circuits as Directed Acyclic Graph (DAG) representations and utilize graph contrastive learning for vector embedding. Then, a tailored list-aware learning-to-rank architecture is employed to generate a list of candidate strategies (prioritizing better strategies). We conduct extensive evaluations involving 45 prevalent quantum algorithm circuits across 3~5 qubits, utilizing 3 IBM quantum physical devices with three types of chip topologies. The results demonstrate that our proposed framework significantly outperforms IBMQ's default deployment scheme, e. g. , achieving 17. 95% overhead reduction and increasing the execution success rate by 20%~40%.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Horae: A Domain-Agnostic Language for Automated Service Regulation

Yutao Sun
Mingshuai Chen
Tiancheng Zhao
Kangjia Zhao
He Li
Jintao Chen
Zhongyi Wang
Liqiang Lu

Artificial intelligence is rapidly encroaching on the field of service regulation. However, existing AI-based regulation techniques are often tailored to specific application domains and thus are difficult to generalize in an automated manner. This paper presents Horae, a unified specification language for modeling (multimodal) regulation rules across a diverse set of domains. We showcase how Horae facilitates an intelligent service regulation pipeline by further exploiting a fine-tuned large language model named RuleGPT that automates the Horae modeling process, thereby yielding an end-to-end framework for fully automated intelligent service regulation. The feasibility and effectiveness of our framework are demonstrated over a benchmark of various real-world regulation domains. In particular, we show that our open-sourced, fine-tuned RuleGPT with 7B parameters suffices to outperform GPT-3. 5 and perform on par with GPT-4o.

PDF Details DOI

IJCAI Conference 2025 Conference Paper

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization

Yuntai Bao
Xuhong Zhang
Tianyu Du
Xinkui Zhao
Jiang Zong
Hao Peng
Jianwei Yin

Pre-trained large language models (LLMs) are commonly fine-tuned to adapt to downstream tasks. Since the majority of knowledge is acquired during pre-training, attributing the predictions of fine-tuned LLMs to their pre-training data may provide valuable insights. Influence functions have been proposed as a means to explain model predictions based on training data. However, existing approaches often fail to compute "multi-stage" influence and lack scalability to billion-scale LLMs. In this paper, we propose multi-stage influence functions to attribute the downstream predictions of fine-tuned LLMs to pre-training data under the full-parameter fine-tuning paradigm. To enhance the efficiency and practicality of our multi-stage influence function, we leverage Eigenvalue-corrected Kronecker-Factored (EK-FAC) parameterization for efficient approximation. Empirical results validate the superior scalability of EK-FAC approximation and the effectiveness of our multi-stage influence function. Additionally, case studies on a real-world LLM, dolly-v2-3b, demonstrate its interpretive power, with exemplars illustrating insights provided by multi-stage influence estimates.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Tool-Planner: Task Planning with Clusters across Multiple Tools

Yanming Liu 0003
Xinyue Peng
Jiannan Cao
Shi Bo
Yuwei Zhang
Xuhong Zhang 0002
Sheng Cheng
Xun Wang

Large language models (LLMs) have demonstrated exceptional reasoning capabilities, enabling them to solve various complex problems. Recently, this ability has been applied to the paradigm of tool learning. Tool learning involves providing examples of tool usage and their corresponding functions, allowing LLMs to formulate plans and demonstrate the process of invoking and executing each tool. LLMs can address tasks that they cannot complete independently, thereby enhancing their potential across different tasks. However, this approach faces two key challenges. First, redundant error correction leads to unstable planning and long execution time. Additionally, designing a correct plan among multiple tools is also a challenge in tool learning. To address these issues, we propose Tool-Planner, a task-processing framework based on toolkits. Tool-Planner groups tools based on the API functions with the same function into a toolkit and allows LLMs to implement planning across the various toolkits. When a tool error occurs, the language model can reselect and adjust tools based on the toolkit. Experiments show that our approach demonstrates a high pass and win rate across different datasets and optimizes the planning scheme for tool learning in models such as GPT-4 and Claude 3, showcasing the potential of our method. Our code is public at https://github.com/OceannTwT/Tool-Planner.

Details

NeurIPS Conference 2025 Conference Paper

UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation

Chengye Wang
Yuyuan Li
XiaoHua Feng
Chaochao Chen
Xiaolin Zheng
Jianwei Yin

Although Multimodal Large Language Models (MLLMs) have advanced numerous fields, their training on extensive multimodal datasets introduces significant privacy concerns, prompting the necessity for efficient unlearning methods. However, current multimodal unlearning approaches often directly adapt techniques from unimodal contexts, largely overlooking the critical issue of modality alignment, i. e. , consistently removing knowledge across both unimodal and multimodal settings. To close this gap, we introduce UMU-bench, a unified benchmark specifically targeting modality misalignment in multimodal unlearning. UMU-bench consists of a meticulously curated dataset featuring 653 individual profiles, each described with both unimodal and multimodal knowledge. Additionally, novel tasks and evaluation metrics focusing on modality alignment are introduced, facilitating a comprehensive analysis of unimodal and multimodal unlearning effectiveness. Through extensive experimentation with state-of-the-art unlearning algorithms on UMU-bench, we demonstrate prevalent modality misalignment issues in existing methods. These findings underscore the critical need for novel multimodal unlearning approaches explicitly considering modality alignment.

PDF Details

NeurIPS Conference 2025 Conference Paper

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation

Ziying Li
Xuequan Lu
Xinkui Zhao
Guanjie Cheng
Shuiguang Deng
Jianwei Yin

Recent advancements in optimization-based text-to-3D generation heavily rely on distilling knowledge from pre-trained text-to-image diffusion models using techniques like Score Distillation Sampling (SDS), which often introduce artifacts such as over-saturation and over-smoothing into the generated 3D assets. In this paper, we address this essential problem by formulating the generation process as learning an optimal, direct transport trajectory between the distribution of the current rendering and the desired target distribution, thereby enabling high-quality generation with smaller Classifier-free Guidance (CFG) values. At first, we theoretically establish SDS as a simplified instance of the Schrödinger Bridge framework. We prove that SDS employs the reverse process of an Schrödinger Bridge, which, under specific conditions (e. g. , a Gaussian noise as one end), collapses to SDS's score function of the pre-trained diffusion model. Based upon this, we introduce Trajectory-Centric Distillation (TraCe), a novel text-to-3D generation framework, which reformulates the mathematically trackable framework of Schrödinger Bridge to explicitly construct a diffusion bridge from the current rendering to its text-conditioned, denoised target, and trains a LoRA-adapted model on this trajectory's score dynamics for robust 3D optimization. Comprehensive experiments demonstrate that TraCe consistently achieves superior quality and fidelity to state-of-the-art techniques. Our code will be released to the community.

PDF Details

I&C Journal 2024 Journal Article

A truthful near-optimal mechanism for online linear packing-covering problem in the random order model

Jinshan Zhang
Xiaoye Miao
Meng Xi
Tianyu Du
Jianwei Yin

Our focus is on the online linear packing-covering problem (OLPCP). Within this domain, we present an algorithm that attains near-optimal performance based on generalized Chernoff bounds for general random variables, assuming inputs are received in a uniformly random order and under almost stringent conditions. Through VCG protocols, we are able to unveil the inaugural truthful near-optimal mechanism for OLPCP, all within the confines of nearly tight conditions.

Details DOI

AAAI Conference 2024 Conference Paper

ECHO-GL: Earnings Calls-Driven Heterogeneous Graph Learning for Stock Movement Prediction

Mengpu Liu
Mengying Zhu
Xiuyuan Wang
Guofang Ma
Jianwei Yin
Xiaolin Zheng

Stock movement prediction serves an important role in quantitative trading. Despite advances in existing models that enhance stock movement prediction by incorporating stock relations, these prediction models face two limitations, i.e., constructing either insufficient or static stock relations, which fail to effectively capture the complex dynamic stock relations because such complex dynamic stock relations are influenced by various factors in the ever-changing financial market. To tackle the above limitations, we propose a novel stock movement prediction model ECHO-GL based on stock relations derived from earnings calls. ECHO-GL not only constructs comprehensive stock relations by exploiting the rich semantic information in the earnings calls but also captures the movement signals between related stocks based on multimodal and heterogeneous graph learning. Moreover, ECHO-GL customizes learnable stock stochastic processes based on the post earnings announcement drift (PEAD) phenomenon to generate the temporal stock price trajectory, which can be easily plugged into any investment strategy with different time horizons to meet investment demands. Extensive experiments on two financial datasets demonstrate the effectiveness of ECHO-GL on stock price movement prediction tasks together with high prediction accuracy and trading profitability.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Enhancing LLM Reasoning via Vision-Augmented Prompting

Ziyang Xiao
Dongxiang Zhang
Xiongwei Han
Xiaojin Fu
Yin Yu
Tao Zhong
Sai Wu
Yuan Wang

Verbal and visual-spatial information processing are two critical subsystems that activate different brain regions and often collaborate together for cognitive reasoning. Despite the rapid advancement of LLM-based reasoning, the mainstream frameworks, such as Chain-of-Thought (CoT) and its variants, primarily focus on the verbal dimension, resulting in limitations in tackling reasoning problems with visual and spatial clues. To bridge the gap, we propose a novel dual-modality reasoning framework called Vision-Augmented Prompting (VAP). Upon receiving a textual problem description, VAP automatically synthesizes an image from the visual and spatial clues by utilizing external drawing tools. Subsequently, VAP formulates a chain of thought in both modalities and iteratively refines the synthesized image. Finally, a conclusive reasoning scheme based on self-alignment is proposed for final result generation. Extensive experiments are conducted across four versatile tasks, including solving geometry problems, Sudoku, time series prediction, and travelling salesman problem. The results validated the superiority of VAP over existing LLMs-based reasoning frameworks.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Fine-Tuning Large Language Model Based Explainable Recommendation with Explainable Quality Reward

Mengyuan Yang
Mengying Zhu
Yan Wang
Linxun Chen
Yilei Zhao
Xiuyuan Wang
Bing Han
Xiaolin Zheng

Large language model-based explainable recommendation (LLM-based ER) systems can provide remarkable human-like explanations and have widely received attention from researchers. However, the original LLM-based ER systems face three low-quality problems in their generated explanations, i.e., lack of personalization, inconsistency, and questionable explanation data. To address these problems, we propose a novel LLM-based ER model denoted as LLM2ER to serve as a backbone and devise two innovative explainable quality reward models for fine-tuning such a backbone in a reinforcement learning paradigm, ultimately yielding a fine-tuned model denoted as LLM2ER-EQR, which can provide high-quality explanations. LLM2ER-EQR can generate personalized, informative, and consistent high-quality explanations learned from questionable-quality explanation datasets. Extensive experiments conducted on three real-world datasets demonstrate that our model can generate fluent, diverse, informative, and highly personalized explanations.

PDF Details DOI

AAAI Conference 2024 Conference Paper

GroundVLP: Harnessing Zero-Shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection

Haozhan Shen
Tiancheng Zhao
Mingwei Zhu
Jianwei Yin

Visual grounding, a crucial vision-language task involving the understanding of the visual context based on the query expression, necessitates the model to capture the interactions between objects, as well as various spatial and attribute information. However, the annotation data of visual grounding task is limited due to its time-consuming and labor-intensive annotation process, resulting in the trained models being constrained from generalizing its capability to a broader domain. To address this challenge, we propose GroundVLP, a simple yet effective zero-shot method that harnesses visual grounding ability from the existing models trained from image-text pairs and pure object detection data, both of which are more conveniently obtainable and offer a broader domain compared to visual grounding annotation data. GroundVLP proposes a fusion mechanism that combines the heatmap from GradCAM and the object proposals of open-vocabulary detectors. We demonstrate that the proposed method significantly outperforms other zero-shot methods on RefCOCO/+/g datasets, surpassing prior zero-shot state-of-the-art by approximately 28% on the test split of RefCOCO and RefCOCO+. Furthermore, GroundVLP performs comparably to or even better than some non-VLP-based supervised models on the Flickr30k entities dataset. Our code is available at https://github.com/om-ai-lab/GroundVLP.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Intra- and Inter-group Optimal Transport for User-Oriented Fairness in Recommender Systems

Zhongxuan Han
Chaochao Chen
Xiaolin Zheng
Meng Li
Weiming Liu
Binhui Yao
Yuyuan Li
Jianwei Yin

Recommender systems are typically biased toward a small group of users, leading to severe unfairness in recommendation performance, i.e., User-Oriented Fairness (UOF) issue. Existing research on UOF exhibits notable limitations in two phases of recommendation models. In the training phase, current methods fail to tackle the root cause of the UOF issue, which lies in the unfair training process between advantaged and disadvantaged users. In the evaluation phase, the current UOF metric lacks the ability to comprehensively evaluate varying cases of unfairness. In this paper, we aim to address the aforementioned limitations and ensure recommendation models treat user groups of varying activity levels equally. In the training phase, we propose a novel Intra- and Inter-GrOup Optimal Transport framework (II-GOOT) to alleviate the data sparsity problem for disadvantaged users and narrow the training gap between advantaged and disadvantaged users. In the evaluation phase, we introduce a novel metric called?-UOF, which enables the identification and assessment of various cases of UOF. This helps prevent recommendation models from leading to unfavorable fairness outcomes, where both advantaged and disadvantaged users experience subpar recommendation performance. We conduct extensive experiments on three real-world datasets based on four backbone recommendation models to prove the effectiveness of?-UOF and the efficiency of our proposed II-GOOT.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics

Jingbo Zhou
Shaorong Chen
Jun Xia
Sizhe Sizhe Liu
Tianze Ling
Wenjie Du
Yue Liu
Jianwei Yin

Tandem mass spectrometry has played a pivotal role in advancing proteomics, enabling the analysis of protein composition in biological tissues. Many deep learning methods have been developed for \emph{de novo} peptide sequencing task, i. e. , predicting the peptide sequence for the observed mass spectrum. However, two key challenges seriously hinder the further research of this important task. Firstly, since there is no consensus for the evaluation datasets, the empirical results in different research papers are often not comparable, leading to unfair comparison. Secondly, the current methods are usually limited to amino acid-level or peptide-level precision and recall metrics. In this work, we present the first unified benchmark NovoBench for \emph{de novo} peptide sequencing, which comprises diverse mass spectrum data, integrated models, and comprehensive evaluation metrics. Recent impressive methods, including DeepNovo, PointNovo, Casanovo, InstaNovo, AdaNovo and $\pi$-HelixNovo are integrated into our framework. In addition to amino acid-level and peptide-level precision and recall, we also evaluate the models' performance in terms of identifying post-tranlational modifications (PTMs), efficiency and robustness to peptide length, noise peaks and missing fragment ratio, which are important influencing factors while seldom be considered. Leveraging this benchmark, we conduct a large-scale study of current methods, report many insightful findings that open up new possibilities for future development. The benchmark is open-sourced to facilitate future research and application. The code is available at \url{https: //github. com/Westlake-OmicsAI/NovoBench}.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Protecting Split Learning by Potential Energy Loss

Fei Zheng
Chaochao Chen
Lingjuan Lyu
Xinyi Fu
Xing Fu
Weiqiang Wang
Xiaolin Zheng
Jianwei Yin

As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and inference. In this paper, we focus on the privacy leakage from the forward embeddings of split learning. Specifically, since the forward embeddings contain too much information about the label, the attacker can either use a few labeled samples to fine-tune the top model or perform unsupervised attacks such as clustering to infer the true labels from the forward embeddings. To prevent such kind of privacy leakage, we propose the potential energy loss to make the forward embeddings more 'complicated', by pushing embeddings of the same class towards the decision boundary. Therefore, it is hard for the attacker to learn from the forward embeddings. Experiment results show that our method significantly lowers the performance of both fine-tuning attacks and clustering attacks.

PDF Details DOI

I&C Journal 2023 Journal Article

Exchange of indivisible goods under matroid constraints

Jinshan Zhang
Bo Tang
Jianwei Yin

We study the problem of reallocating indivisible goods among a set of strategic agents by generalizing the original Sharpley-Scarf market to the setting where an object can be allocated to multiple agents but subject to an associated matroid constraint. We refer to this modified market as the matroid Sharpley-Scarf market. For this general market, we present a Pareto-optimal, individually rational and group strategy-proof mechanism. Our mechanism is simple and natural generalization of the Top Trading Cycle mechanism and the Serial Dictator mechanism. In our analysis, we demonstrate that the weak core may be absent in the matroid Sharpley-Scarf market, while a relaxed version called the constrained core does exist. Furthermore, we extend the concept called competitive equilibrium to the matroid Sharpley-Scarf market and show that an allocation is a competitive equilibrium if and only if it can be produced by our mechanism.

Details DOI

IJCAI Conference 2023 Conference Paper

Federated Probabilistic Preference Distribution Modelling with Compactness Co-Clustering for Privacy-Preserving Multi-Domain Recommendation

Weiming Liu
Chaochao Chen
Xinting Liao
Mengling Hu
Jianwei Yin
Yanchao Tan
Longfei Zheng

With the development of modern internet techniques, Cross-Domain Recommendation (CDR) systems have been widely exploited for tackling the data-sparsity problem. Meanwhile most current CDR models assume that user-item interactions are accessible across different domains. However, such knowledge sharing process will break the privacy protection policy. In this paper, we focus on the Privacy-Preserving Multi-Domain Recommendation problem (PPMDR). The problem is challenging since different domains are sparse and heterogeneous with the privacy protection. To tackle the above issues, we propose Federated Probabilistic Preference Distribution Modelling (FPPDM). FPPDM includes two main components, i. e. , local domain modelling component and global server aggregation component with federated learning strategy. The local domain modelling component aims to exploit user/item preference distributions using the rating information in the corresponding domain. The global server aggregation component is set to combine user characteristics across domains. To better extract semantic neighbors information among the users, we further provide compactness co-clustering strategy in FPPDM ++ to cluster the users with similar characteristics. Our empirical studies on benchmark datasets demonstrate that FPPDM/ FPPDM ++ significantly outperforms the state-of-the-art models.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Jointly Imputing Multi-View Data with Optimal Transport

Yangyang Wu
Xiaoye Miao
Xinyu Huang
Jianwei Yin

The multi-view data with incomplete information hinder the effective data analysis. Existing multi-view imputation methods that learn the mapping between complete view and completely missing view are not able to deal with the common multi-view data with missing feature information. In this paper, we propose a generative imputation model named Git with optimal transport theory to jointly impute the missing features/values, conditional on all observed values from the multi-view data. Git consists of two modules, i.e., a multi-view joint generator (MJG) and a masking energy discriminator (MED). The generator MJG incorporates a joint autoencoder with the multiple imputation rule to learn the data distribution from all observed multi-view data. The discriminator MED leverages a new masking energy divergence function to make Git differentiable for imputation enhancement. Extensive experiments on several real-world multi-view data sets demonstrate that, Git yields over 35% accuracy gain, compared to the state-of-the-art approaches.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Truthful Mechanisms for Steiner Tree Problems

Jinshan Zhang
Zhengyang Liu
Xiaotie Deng
Jianwei Yin

Consider an undirected graph G=(V,E) model for a communication network, where each edge is owned by a selfish agent, who reports the cost for offering the use of her edge. Note that each edge agent may misreport her own cost for the use of the edge for her own benefit. In such a non-cooperative setting, we aim at designing an approximately truthful mechanism for establishing a Steiner tree, a minimum cost tree spanning over all the terminals. We present a truthful-in-expectation mechanism that achieves the approximation ratio ln 4 + ε ≈ 1.39, which matches the current best algorithmic ratio for STP.

PDF Details DOI

TIST Journal 2022 Journal Article

Toward Scalable and Privacy-preserving Deep Neural Network via Algorithmic-Cryptographic Co-design

Jun Zhou
Longfei Zheng
Chaochao Chen
Yan Wang
Xiaolin Zheng
Bingzhe Wu
Cen Chen
Li Wang

Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy-preserving DNN models from either algorithmic perspective or cryptographic perspective. The former mainly splits the DNN computation graph between data holders or between data holders and server, which demonstrates good scalability but suffers from accuracy loss and potential privacy risks. In contrast, the latter leverages time-consuming cryptographic techniques, which has strong privacy guarantee but poor scalability. In this article, we propose SPNN—a Scalable and Privacy-preserving deep Neural Network learning framework, from an algorithmic-cryptographic co-perspective. From algorithmic perspective, we split the computation graph of DNN models into two parts, i.e., the private-data-related computations that are performed by data holders and the rest heavy computations that are delegated to a semi-honest server with high computation ability. From cryptographic perspective, we propose using two types of cryptographic techniques, i.e., secret sharing and homomorphic encryption, for the isolated data holders to conduct private-data-related computations privately and cooperatively. Furthermore, we implement SPNN in a decentralized setting and introduce user-friendly APIs. Experimental results conducted on real-world datasets demonstrate the superiority of our proposed SPNN.

Details DOI

AAAI Conference 2021 Conference Paper

Generative Semi-supervised Learning for Multivariate Time Series Imputation

Xiaoye Miao
Yangyang Wu
Jun Wang
Yunjun Gao
Xudong Mao
Jianwei Yin

The missing values, widely existed in multivariate time series data, hinder the effective data analysis. Existing time series imputation methods do not make full use of the label information in real-life time series data. In this paper, we propose a novel semi-supervised generative adversarial network model, named SSGAN, for missing value imputation in multivariate time series data. It consists of three players, i. e. , a generator, a discriminator, and a classifier. The classifier predicts labels of time series data, and thus it drives the generator to estimate the missing values (or components), conditioned on observed components and data labels at the same time. We introduce a temporal reminder matrix to help the discriminator better distinguish the observed components from the imputed ones. Moreover, we theoretically prove that, SSGAN using the temporal reminder matrix and the classifier does learn to estimate missing values converging to the true data distribution when the Nash equilibrium is achieved. Extensive experiments on three public real-world datasets demonstrate that, SSGAN yields a more than 15% gain in performance, compared with the state-of-the-art methods.

PDF Details

IJCAI Conference 2020 Conference Paper

Joint Partial Optimal Transport for Open Set Domain Adaptation

Renjun Xu
Pelen Liu
Yin Zhang
Fang Cai
Jindong Wang
Shuoying Liang
Heting Ying
Jianwei Yin

Domain adaptation (DA) has achieved a resounding success to learn a good classifier by leveraging labeled data from a source domain to adapt to an unlabeled target domain. However, in a general setting when the target domain contains classes that are never observed in the source domain, namely in Open Set Domain Adaptation (OSDA), existing DA methods failed to work because of the interference of the extra unknown classes. This is a much more challenging problem, since it can easily result in negative transfer due to the mismatch between the unknown and known classes. Existing researches are susceptible to misclassification when target domain unknown samples in the feature space distributed near the decision boundary learned from the labeled source domain. To overcome this, we propose Joint Partial Optimal Transport (JPOT), fully utilizing information of not only the labeled source domain but also the discriminative representation of unknown class in the target domain. The proposed joint discriminative prototypical compactness loss can not only achieve intra-class compactness and inter-class separability, but also estimate the mean and variance of the unknown class through backpropagation, which remains intractable for previous methods due to the blindness about the structure of the unknown classes. To our best knowledge, this is the first optimal transport model for OSDA. Extensive experiments demonstrate that our proposed model can significantly boost the performance of open set domain adaptation on standard DA datasets.

PDF Details DOI

EAAI Journal 2017 Journal Article

Tackling topic general words in topic modeling

Yueshen Xu
Yuyu Yin
Jianwei Yin

Topic models are a prevailing tool for exploring latent topics in documents, and for helping to complete many NLP tasks. To obtain good topics for a corpus, a preprocessing step is often needed to remove common stop words and identify topic general words (TGW) from the corpus. Such words can seriously harm the topic formation because they create spurious co-occurrence of unrelated words. Also, they are likely to occupy top positions of multiple topics, lead to many unrelated words being grouped under a topic, and consequently result in inscrutable and similar topics. In an application, one typically manually identifies and removes a list of TGWs in the corpus. This is a time consuming process and very hard to do by a layman user. In this paper, we aim to solve this problem automatically. The proposed approaches can be based on the current corpus alone or multiple corpora. In the latter case, a novel continuous learning method is proposed that learns from past results of multiple domain corpora to help identify TGWs in the current domain. We conduct experiments in two real-world datasets, and the experimental results show that the proposed approaches achieve superior results.

Details DOI

EAAI Journal 2015 Journal Article

Collaborative recommendation with user generated content

Yueshen Xu
Jianwei Yin

In the age of Web 2. 0, user generated content (UGC), such as user review and social tag, ubiquitously exists on the Internet. Although there exist different kinds of UGC in recommender systems, the existing works only studied a single kind of UGC in each of their papers. Thus, the previous works lose a chance to uncover the similar effects of different kinds of UGC in recommender systems. In this paper, we propose a unified way to utilize various types of UGC to enhance the recommendation accuracy. We build two novel statistical models, which are based on collaborative filtering and topic modeling. Incorporating UGC text, one model focuses on learning user preferences, and the other model aims to learn user preferences and item aspects jointly. With an effective parameter estimation algorithm, our models can not only acquire prediction values of missing ratings, but also produce interpretable topics. We conducted comprehensive experiments on three real-world datasets. The experimental results demonstrate that our proposed models can achieve large improvements compared to several well-known baseline models.

Details DOI

EAAI Journal 2015 Journal Article

Efficient web service QoS prediction using local neighborhood matrix factorization

Wei Lo
Jianwei Yin
Ying Li
Zhaohui Wu

In the era of Big Data, companies worldwide are actively deploying web services in both intranet and internet environments. Quality-of-Service (QoS), the fundamental aspect of web service has thus attracted numerous attention in industry and academia. The study on sufficient QoS data keeps advancing the state in Service-Oriented Computing (SOC) area. To collect a large amount of resource in practice, QoS prediction applications are designed and built. Nevertheless, how to generate accurate results in high productivity is still a main challenge to existing frameworks. In this paper, we propose LoNMF, a Local Neighborhood Matrix Factorization application that incorporates domain knowledge in modern Artificial Intelligence (AI) technique to tackle this challenge. LoNMF first proposes a two-level selection mechanism that can identify a set of highly relevant local neighbors for target user. And then, it integrates the geographical information to build up an extended Matrix Factorization (MF) approach for personalized QoS prediction. Finally, it iteratively generates results by utilizing hints from previous round computations, a gradient boosting strategy that directly accelerates solving process. Experimental evidence on large-scale real-world QoS data shows that LoNMF is scalable, and consistently outperforming other state-of-the-art applications in prediction accuracy and efficiency.

Details DOI

EAAI Journal 2011 Journal Article

JTangCSPS: A composite and semantic publish/subscribe system over structured P2P networks

Jianfeng Qian
Jianwei Yin
Jinxiang Dong
Dongcai Shi

Publish/subscribe systems offer a loosely coupled communication paradigm in distributed information systems. However, supporting expression of semantic events, expression of logical and temporal patterns of composite events, and how to manage and route composite events and subscriptions still need further research. In this paper, we present the design and implementation of JTang composite and semantic publish/subscribe system over structured P2P networks, and highlight its novel features, including semantic broker network, composite event and subscription language and distributed composite subscription management. The experiments based on the Peersim simulator over the Pastry overlays show that the ontology routing table helps decrease the average number of hops and the use of composite subscriptions significantly reduces the load on the network.

Details DOI