Search Results for author: Zhen Wang

Found 206 papers, 76 papers with code

Deep Streaming Label Learning

1 code implementation ICML 2020 Zhen Wang, Liu Liu, DaCheng Tao

In order to fill in these research gaps, we propose a novel deep neural network (DNN) based framework, Deep Streaming Label Learning (DSLL), to classify instances with newly emerged labels effectively.

Multi-Label Learning

Zero-Shot Solving of Imaging Inverse Problems via Noise-Refined Likelihood Guided Diffusion Models

no code implementations16 Jun 2025 Zhen Wang, Hongyi Liu, Zhihui Wei

We introduce a likelihood-guided noise refinement mechanism that derives a closed-form approximation of the likelihood score, simplifying score estimation and avoiding expensive gradient computations.

Compressive Sensing Denoising

Single-Node Trigger Backdoor Attacks in Graph-Based Recommendation Systems

no code implementations10 Jun 2025 Runze Li, Di Jin, Xiaobao Wang, Dongxiao He, Bingdao Feng, Zhen Wang

To address these challenges, this paper proposes a novel graph backdoor attack method that aims to enhance the exposure of target items to the target user in a covert manner, without affecting other unrelated nodes.

Backdoor Attack Recommendation Systems

Towards a Generalizable Bimanual Foundation Policy via Flow-based Video Prediction

no code implementations30 May 2025 Chenyou Fan, Fangzheng Yan, Chenjia Bai, Jiepeng Wang, Chi Zhang, Zhen Wang, Xuelong Li

However, transferring knowledge from single-arm datasets or pre-trained VLA models often fails to generalize effectively, primarily due to the scarcity of bimanual data and the fundamental differences between single-arm and bimanual manipulation.

Action Generation Optical Flow Estimation +2

Taming Recommendation Bias with Causal Intervention on Evolving Personal Popularity

1 code implementation20 May 2025 Shiyin Tan, Dongyuan Li, Renhe Jiang, Zhen Wang, Xingtong Yu, Manabu Okumura

To address these issues, we propose a novel method called CausalEPP (Causal Intervention on Evolving Personal Popularity) for taming recommendation bias, which accounts for the evolving personal popularity of users.

HyperDet: Source Detection in Hypergraphs via Interactive Relationship Construction and Feature-rich Attention Fusion

no code implementations19 May 2025 Le Cheng, Peican Zhu, Yangming Guo, Keke Tang, Chao GAO, Zhen Wang

Hypergraphs offer superior modeling capabilities for social networks, particularly in capturing group phenomena that extend beyond pairwise interactions in rumor propagation.

Decentralized Arena: Towards Democratic and Scalable Automatic Evaluation of Language Models

1 code implementation19 May 2025 Yanbin Yin, Kun Zhou, Zhen Wang, Xiangdong Zhang, Yifei Shao, Shibo Hao, Yi Gu, Jieyuan Liu, Somanshu Singla, Tianyang Liu, Eric P. Xing, Zhengzhong Liu, Haojian Jin, Zhiting Hu

The recent explosion of large language models (LLMs), each with its own general or specialized strengths, makes scalable, reliable benchmarking more urgent than ever.

Benchmarking Chatbot +2

A 3D pocket-aware and evolutionary conserved interaction guided diffusion model for molecular optimization

no code implementations9 May 2025 Anjie Qiao, Hao Zhang, Qianmu Yuan, Qirui Deng, Jingtian Su, Weifeng Huang, Huihao Zhou, Guo-Bo Li, Zhen Wang, Jinping Lei

Generating molecules that bind to specific protein targets via diffusion models has shown good promise for structure-based drug design and molecule optimization.

Drug Design

Beyond the Tragedy of the Commons: Building A Reputation System for Generative Multi-agent Systems

no code implementations8 May 2025 Siyue Ren, Wanli Fu, Xinkun Zou, Chen Shen, Yi Cai, Chen Chu, Zhen Wang, Shuyue Hu

The tragedy of the commons, where individual self-interest leads to collectively disastrous outcomes, is a pervasive challenge in human society.

On the Robustness of GUI Grounding Models Against Image Attacks

1 code implementation7 Apr 2025 Haoren Zhao, Tianyi Chen, Zhen Wang

Graphical User Interface (GUI) grounding models are crucial for enabling intelligent agents to understand and interact with complex visual interfaces.

Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields

no code implementations CVPR 2025 Shijie Zhou, Hui Ren, Yijia Weng, Shuwang Zhang, Zhen Wang, Dejia Xu, Zhiwen Fan, Suya You, Zhangyang Wang, Leonidas Guibas, Achuta Kadambi

In this paper, we introduce Feature4X, a universal framework designed to extend any functionality from 2D vision foundation model into the 4D realm, using only monocular video input, which is widely available from user-generated content.

Question Answering Visual Question Answering

Does GCL Need a Large Number of Negative Samples? Enhancing Graph Contrastive Learning with Effective and Efficient Negative Sampling

1 code implementation23 Mar 2025 Yongqi Huang, Jitao Zhao, Dongxiao He, Di Jin, Yuxiao Huang, Zhen Wang

To answer this, we explore the role of negative nodes in the commonly used InfoNCE loss for GCL and observe that: (1) Counterintuitively, a large number of negative nodes can actually hinder the model's ability to distinguish nodes with different semantics.

Contrastive Learning

Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances

no code implementations24 Feb 2025 Yaozu Wu, Dongyuan Li, Yankai Chen, Renhe Jiang, Henry Peng Zou, Liancheng Fang, Zhen Wang, Philip S. Yu

Autonomous Driving Systems (ADSs) are revolutionizing transportation by reducing human intervention, improving operational efficiency, and enhancing safety.

Autonomous Driving Decision Making

If Multi-Agent Debate is the Answer, What is the Question?

no code implementations12 Feb 2025 Hangfan Zhang, Zhiyao Cui, Xinrun Wang, Qiaosheng Zhang, Zhen Wang, Dinghao Wu, Shuyue Hu

Multi-agent debate (MAD) has emerged as a promising approach to enhance the factual accuracy and reasoning quality of large language models (LLMs) by engaging multiple agents in iterative discussions during inference.

SMI: An Information-Theoretic Metric for Predicting Model Knowledge Solely from Pre-Training Signals

1 code implementation6 Feb 2025 Changhao Jiang, Ming Zhang, Junjie Ye, Xiaoran Fan, Yifei Cao, Jiajun Sun, Zhiheng Xi, Shihan Dou, Yi Dong, Yujiong Shen, Jingqi Tong, Zhen Wang, Tao Liang, Zhihui Fei, Mingyang Wan, Guojun Ma, Qi Zhang, Tao Gui, Xuanjing Huang

The GPT-4 technical report highlights the possibility of predicting model performance on downstream tasks using only pre-training signals, though detailed methodologies are absent.

Question Answering

PQD: Post-training Quantization for Efficient Diffusion Models

no code implementations30 Dec 2024 Jiaojiao Ye, Zhen Wang, Linnan Jiang

Experimental results show that our proposed method is able to directly quantize full-precision diffusion models into 8-bit or 4-bit models while maintaining comparable performance in a training-free manner, achieving a few FID change on ImageNet for unconditional image generation.

Diversity Image Generation +2

Graph Attention is Not Always Beneficial: A Theoretical Analysis of Graph Attention Mechanisms via Contextual Stochastic Block Models

1 code implementation20 Dec 2024 Zhongtian Ma, Qiaosheng Zhang, Bocheng Zhou, Yexin Zhang, Shuyue Hu, Zhen Wang

Specifically, by appropriately defining \emph{structure noise} and \emph{feature noise} in graphs, we show that graph attention mechanisms can enhance classification performance when structure noise exceeds feature noise.

Graph Attention Node Classification

EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation Prediction

no code implementations15 Dec 2024 Qingwen Tian, Yuxin Xu, Yixuan Yang, Zhen Wang, Ziqi Liu, Pengju Yan, Xiaolin Li

EquiFlow uniquely applies conditional flow matching in molecular 3D conformation prediction, leveraging simulation-free training to address slow training speeds.

From Exploration to Revelation: Detecting Dark Patterns in Mobile Apps

no code implementations27 Nov 2024 Jieshan Chen, Zhen Wang, Jiamou Sun, Wenbo Zou, Zhenchang Xing, Qinghua Lu, Qing Huang, Xiwei Xu

While some studies targeted at automated detection, they are constrained to static patterns and still necessitate manual app exploration.

Contrastive Learning

Less is More: Efficient Model Merging with Binary Task Switch

no code implementations CVPR 2025 Biqing Qi, Fangyuan Li, Zhen Wang, Junqi Gao, Dong Li, Peng Ye, BoWen Zhou

However, existing methods face challenges of redundant parameter conflicts and the excessive storage burden of parameters.

IterIS: Iterative Inference-Solving Alignment for LoRA Merging

no code implementations CVPR 2025 Hongxu Chen, Runshi Li, Bowei Zhu, Zhen Wang, Long Chen

Prior works on LoRA merging primarily frame it as an optimization problem, yet these approaches face several limitations, including the rough assumption about input features utilized in optimization, massive sample requirements, and the unbalanced optimization objective.

Dynamic Rewarding with Prompt Optimization Enables Tuning-free Self-Alignment of Language Models

1 code implementation13 Nov 2024 Somanshu Singla, Zhen Wang, Tianyang Liu, Abdullah Ashfaq, Zhiting Hu, Eric P. Xing

To further lower costs and achieve alignment without any expensive tuning or annotations, we introduce a new tuning-free approach for self-alignment, Dynamic Rewarding with Prompt Optimization (DRPO).

Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction

1 code implementation3 Nov 2024 Haotong Du, Quanming Yao, Juzheng Zhang, Yang Liu, Zhen Wang

Subgraph-based methods have proven to be effective and interpretable in predicting drug-drug interactions (DDIs), which are essential for medical practice and drug development.

Neural Architecture Search

Prediction by Machine Learning Analysis of Genomic Data Phenotypic Frost Tolerance in Perccottus glenii

no code implementations11 Oct 2024 Lilin Fan, Xuqing Chai, Zhixiong Tian, Yihang Qiao, Zhen Wang, Yifan Zhang

Analysis of the genome sequence of Perccottus glenii, the only fish known to possess freeze tolerance, holds significant importance for understanding how organisms adapt to extreme environments, Traditional biological analysis methods are time-consuming and have limited accuracy, To address these issues, we will employ machine learning techniques to analyze the gene sequences of Perccottus glenii, with Neodontobutis hainanens as a comparative group, Firstly, we have proposed five gene sequence vectorization methods and a method for handling ultra-long gene sequences, We conducted a comparative study on the three vectorization methods: ordinal encoding, One-Hot encoding, and K-mer encoding, to identify the optimal encoding method, Secondly, we constructed four classification models: Random Forest, LightGBM, XGBoost, and Decision Tree, The dataset used by these classification models was extracted from the National Center for Biotechnology Information database, and we vectorized the sequence matrices using the optimal encoding method, K-mer, The Random Forest model, which is the optimal model, achieved a classification accuracy of up to 99, 98 , Lastly, we utilized SHAP values to conduct an interpretable analysis of the optimal classification model, Through ten-fold cross-validation and the AUC metric, we identified the top 10 features that contribute the most to the model's classification accuracy, This demonstrates that machine learning methods can effectively replace traditional manual analysis in identifying genes associated with the freeze tolerance phenotype in Perccottus glenii.

Classification

Test-Time Intensity Consistency Adaptation for Shadow Detection

no code implementations10 Oct 2024 Leyi Zhu, Weihuang Liu, Xinyi Chen, Zimeng Li, Xuhang Chen, Zhen Wang, Chi-Man Pun

Shadow detection is crucial for accurate scene understanding in computer vision, yet it is challenged by the diverse appearances of shadows caused by variations in illumination, object geometry, and scene context.

Decoder Diversity +3

Diffusion Models in 3D Vision: A Survey

no code implementations7 Oct 2024 Zhen Wang, Dongyuan Li, Yaozu Wu, Tianyu He, Jiang Bian, Renhe Jiang

In recent years, 3D vision has become a crucial field within computer vision, powering a wide range of applications such as autonomous driving, robotics, augmented reality, and medical imaging.

Autonomous Driving Computational Efficiency +3

Combing Text-based and Drag-based Editing for Precise and Flexible Image Editing

no code implementations4 Oct 2024 Ziqi Jiang, Zhen Wang, Long Chen

To address these issues, we proposed \textbf{CLIPDrag}, a novel image editing method that is the first to combine text and drag signals for precise and ambiguity-free manipulations on diffusion models.

Point Tracking

Event-Customized Image Generation

no code implementations3 Oct 2024 Zhen Wang, Yilei Jiang, Dong Zheng, Jun Xiao, Long Chen

To extend customized image generation to more complex scenes for general real-world applications, we propose a new task: event-customized image generation.

Denoising Image Generation

Task-agnostic Pre-training and Task-guided Fine-tuning for Versatile Diffusion Planner

no code implementations30 Sep 2024 Chenyou Fan, Chenjia Bai, Zhao Shan, Haoran He, Yang Zhang, Zhen Wang

Then for downstream tasks, we adopt RL-based fine-tuning with task-specific rewards to quickly refine the diffusion planner, which aims to generate action sequences with higher task-specific returns.

Reinforcement Learning (RL)

Overcoming the Machine Penalty with Imperfectly Fair AI Agents

no code implementations29 Sep 2024 Zhen Wang, Ruiqi Song, Chen Shen, Shiya Yin, Zhao Song, Balaraju Battu, Lei Shi, Danyang Jia, Talal Rahwan, Shuyue Hu

Despite rapid technological progress, effective human-machine cooperation remains a significant challenge.

CUS3D :CLIP-based Unsupervised 3D Segmentation via Object-level Denoise

no code implementations21 Sep 2024 Fuyang Yu, Runze Tian, Zhen Wang, Xiaochuan Wang, Xiaohui Liang

To ease the difficulty of acquiring annotation labels in 3D data, a common method is using unsupervised and open-vocabulary semantic segmentation, which leverage 2D CLIP semantic knowledge.

Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation +1

A high-accuracy multi-model mixing retrosynthetic method

no code implementations6 Sep 2024 Shang Xiang, Lin Yao, Zhen Wang, Qifan Yu, Wentan Liu, Wentao Guo, Guolin Ke

The field of computer-aided synthesis planning (CASP) has seen rapid advancements in recent years, achieving significant progress across various algorithmic benchmarks.

Diversity model +1

Application Research On Real-Time Perception Of Device Performance Status

no code implementations5 Sep 2024 Zhe Wang, Zhen Wang, Jianwen Wu, Wangzhong Xiao, Yidong Chen, Zihua Feng, Dian Yang, Hongchen Liu, Bo Liang, Jiaojiao Fu

In order to accurately identify the performance status of mobile devices and finely adjust the user experience, a real-time performance perception evaluation method based on TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) combined with entropy weighting method and time series model construction was studied.

Descriptive Dimensionality Reduction +3

S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search

no code implementations27 Aug 2024 Gengmo Zhou, Zhen Wang, Feng Yu, Guolin Ke, Zhewei Wei, Zhifeng Gao

Virtual Screening is an essential technique in the early phases of drug discovery, aimed at identifying promising drug candidates from vast molecular libraries.

Contrastive Learning Data Augmentation +2

LalaEval: A Holistic Human Evaluation Framework for Domain-Specific Large Language Models

no code implementations23 Aug 2024 Chongyan Sun, Ken Lin, Shiwei Wang, Hulong Wu, Chengfei Fu, Zhen Wang

This paper introduces LalaEval, a holistic framework designed for the human evaluation of domain-specific large language models (LLMs).

Model Selection

Understanding Literary Texts by LLMs: A Case Study of Ancient Chinese Poetry

1 code implementation22 Aug 2024 Cheng Zhao, Bin Wang, Zhen Wang

Additionally, evaluating literary works is often complex and hard to fully quantify, which directly hinders the further development of AI creation.

Analytical and Empirical Study of Herding Effects in Recommendation Systems

no code implementations20 Aug 2024 Hong Xie, Mingze Zhong, Defu Lian, Zhen Wang, Enhong Chen

We also study the speed of convergence numerically and reveal trade-offs in selecting rating aggregation rules and review selection mechanisms.

Recommendation Systems

Cross-Scan Mamba with Masked Training for Robust Spectral Imaging

no code implementations1 Aug 2024 Wenzhe Tian, Haijin Zeng, Yin-Ping Zhao, Yongyong Chen, Zhen Wang, Xuelong Li

Current CNN-based methods are limited in modeling long-range dependencies, while Transformer-based models face high computational complexity.

Computational Efficiency Mamba

Pavement Fatigue Crack Detection and Severity Classification Based on Convolutional Neural Network

no code implementations22 Jul 2024 Zhen Wang, Dylan G. Ildefonzo, Linbing Wang

The first objective of the proposed neural network is to classify presence of fatigue cracking based on pavement surface images.

Classification image-classification +1

Foundations and Frontiers of Graph Learning Theory

no code implementations3 Jul 2024 Yu Huang, Min Zhou, Menglin Yang, Zhen Wang, Muhan Zhang, Jie Wang, Hong Xie, Hao Wang, Defu Lian, Enhong Chen

Recent advancements in graph learning have revolutionized the way to understand and analyze data with complex structures.

Graph Learning Learning Theory

Probing many-body Bell correlation depth with superconducting qubits

no code implementations25 Jun 2024 Ke Wang, Weikang Li, Shibo Xu, Mengyao Hu, Jiachen Chen, Yaozu Wu, Chuanyu Zhang, Feitong Jin, Xuhao Zhu, Yu Gao, Ziqi Tan, Aosai Zhang, Ning Wang, Yiren Zou, TingTing Li, Fanhao Shen, Jiarun Zhong, Zehang Bao, Zitian Zhu, Zixuan Song, Jinfeng Deng, Hang Dong, Xu Zhang, Pengfei Zhang, Wenjie Jiang, Zhide Lu, Zheng-Zhi Sun, Hekang Li, Qiujiang Guo, Zhen Wang, Patrick Emonts, Jordi Tura, Chao Song, H. Wang, Dong-Ling Deng

As an illustrating example, we variationally prepare the low-energy state of a two-dimensional honeycomb model with 73 qubits and certify its Bell correlations by measuring an energy that surpasses the corresponding classical bound with up to 48 standard deviations.

Uni-Mol2: Exploring Molecular Pretraining Model at Scale

2 code implementations21 Jun 2024 Xiaohong Ji, Zhen Wang, Zhifeng Gao, Hang Zheng, Linfeng Zhang, Guolin Ke, Weinan E

In recent years, pretraining models have made significant advancements in the fields of natural language processing (NLP), computer vision (CV), and life sciences.

model

Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts

no code implementations17 Jun 2024 Junmo Kang, Leonid Karlinsky, Hongyin Luo, Zhen Wang, Jacob Hansen, James Glass, David Cox, Rameswar Panda, Rogerio Feris, Alan Ritter

Our findings highlight the critical role of modularity, the applicability of Self-MoE to multiple base LLMs, and the potential of self-improvement in achieving efficient, scalable, and adaptable systems.

Math

FreeTuner: Any Subject in Any Style with Training-free Diffusion

no code implementations23 May 2024 Youcan Xu, Zhen Wang, Jun Xiao, Wei Liu, Long Chen

With the advance of diffusion models, various personalized image generation methods have been proposed.

Disentanglement Image Generation +1

Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration

no code implementations23 May 2024 Yang Zhang, Shixin Yang, Chenjia Bai, Fei Wu, Xiu Li, Zhen Wang, Xuelong Li

In this paper, we propose a novel framework for multi-agent collaboration that introduces Reinforced Advantage feedback (ReAd) for efficient self-refinement of plans.

regression

Learning Partially Aligned Item Representation for Cross-Domain Sequential Recommendation

no code implementations21 May 2024 Mingjia Yin, Hao Wang, Wei Guo, Yong liu, Zhi Li, Sirui Zhao, Zhen Wang, Defu Lian, Enhong Chen

Cross-domain sequential recommendation (CDSR) aims to uncover and transfer users' sequential preferences across multiple recommendation domains.

Multi-Task Learning Self-Supervised Learning +1

Ensemble Successor Representations for Task Generalization in Offline-to-Online Reinforcement Learning

no code implementations12 May 2024 Changhong Wang, Xudong Yu, Chenjia Bai, Qiaosheng Zhang, Zhen Wang

To address this problem, our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning.

Offline RL Reinforcement Learning (RL) +1

Contrastive Representation for Data Filtering in Cross-Domain Offline Reinforcement Learning

1 code implementation10 May 2024 Xiaoyu Wen, Chenjia Bai, Kang Xu, Xudong Yu, Yang Zhang, Xuelong Li, Zhen Wang

In this paper, we propose a novel representation-based approach to measure the domain gap, where the representation is learned through a contrastive objective by sampling transitions from different domains.

reinforcement-learning

Pessimistic Value Iteration for Multi-Task Data Sharing in Offline Reinforcement Learning

1 code implementation30 Apr 2024 Chenjia Bai, Lingxiao Wang, Jianye Hao, Zhuoran Yang, Bin Zhao, Zhen Wang, Xuelong Li

We further provide theoretical analysis, which shows that the optimality gap of our method is only related to the expected data coverage of the shared dataset, thus resolving the distribution shift issue in data sharing.

Offline RL Reinforcement Learning (RL) +1

Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning

no code implementations30 Apr 2024 Qiaosheng Zhang, Chenjia Bai, Shuyue Hu, Zhen Wang, Xuelong Li

Finally, we extend Reg-MAIDS to multi-player general-sum MGs and prove that it can learn either the Nash equilibrium or coarse correlated equilibrium in a sample efficient manner.

Multi-agent Reinforcement Learning

A General Black-box Adversarial Attack on Graph-based Fake News Detectors

no code implementations24 Apr 2024 Peican Zhu, Zechen Pan, Yang Liu, Jiwei Tian, Keke Tang, Zhen Wang

Specifically, as sharing is an important social interaction for GNN-based fake news detectors to construct the graph, we simulate sharing behaviors to fool the detectors.

Adversarial Attack Graph Neural Network

Diverse Randomized Value Functions: A Provably Pessimistic Approach for Offline Reinforcement Learning

no code implementations9 Apr 2024 Xudong Yu, Chenjia Bai, Hongyi Guo, Changhong Wang, Zhen Wang

Offline Reinforcement Learning (RL) faces distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions.

Diversity Reinforcement Learning (RL) +1

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models

1 code implementation8 Apr 2024 Shibo Hao, Yi Gu, Haotian Luo, Tianyang Liu, Xiyan Shao, Xinyuan Wang, Shuhua Xie, Haodi Ma, Adithya Samavedhi, Qiyue Gao, Zhen Wang, Zhiting Hu

(2) We develop LLM Reasoners, a library for standardized modular implementation of existing and new reasoning algorithms, under a unified formulation of the search, reward, and world model components.

AUEditNet: Dual-Branch Facial Action Unit Intensity Manipulation with Implicit Disentanglement

no code implementations CVPR 2024 Shiwei Jin, Zhen Wang, Lei Wang, Peng Liu, Ning Bi, Truong Nguyen

Our experiments demonstrate AUEditNet's superior accuracy in editing AU intensities, affirming its capability in disentangling facial attributes and identity within a limited subject pool.

Attribute Disentanglement

Graph Regularized NMF with L20-norm for Unsupervised Feature Learning

no code implementations16 Mar 2024 Zhen Wang, Wenwen Min

Nonnegative Matrix Factorization (NMF) is a widely applied technique in the fields of machine learning and data mining.

Dimensionality Reduction feature selection

Emergence of Social Norms in Generative Agent Societies: Principles and Architecture

1 code implementation13 Mar 2024 Siyue Ren, Zhiyao Cui, Ruiqi Song, Zhen Wang, Shuyue Hu

Our experiments deployed in the Smallville sandbox game environment demonstrate the capability of our architecture to establish social norms and reduce social conflicts within generative MASs.

Language Modelling Large Language Model

GIN-SD: Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion

no code implementations27 Feb 2024 Le Cheng, Peican Zhu, Keke Tang, Chao GAO, Zhen Wang

In this paper, we address a more challenging task, rumor source detection with incomplete user data, and propose a novel framework, i. e., Source Detection in Graphs with Incomplete Nodes via Positional Encoding and Attentive Fusion (GIN-SD), to tackle this challenge.

Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas

no code implementations27 Feb 2024 Chunjiang Mu, Hao Guo, Yang Chen, Chen Shen, Shuyue Hu, Zhen Wang

Third, we review the emergent field of leveraging AI agents to enhance cooperation among humans.

Cofca: A Step-Wise Counterfactual Multi-hop QA benchmark

no code implementations19 Feb 2024 Jian Wu, Linyi Yang, Zhen Wang, Manabu Okumura, Yue Zhang

Although previous counterfactual QA benchmarks can separate the internal memory of LLMs, they focus solely on final QA performance, which is insufficient for reporting LLMs' real reasoning abilities.

counterfactual Multi-hop Question Answering +2

Improving Data Augmentation for Robust Visual Question Answering with Effective Curriculum Learning

no code implementations28 Jan 2024 Yuhang Zheng, Zhen Wang, Long Chen

Compared to training on the entire augmented dataset, our ECL strategy can further enhance VQA models' performance with fewer training samples.

Data Augmentation Question Answering +1

Diffusion-based Data Augmentation for Object Counting Problems

no code implementations25 Jan 2024 Zhen Wang, Yuelei Li, Jia Wan, Nuno Vasconcelos

Our proposed smoothed density map input for ControlNet significantly improves ControlNet's performance in generating crowds in the correct locations.

Crowd Counting Data Augmentation +2

Community Detection in the Multi-View Stochastic Block Model

no code implementations17 Jan 2024 Yexin Zhang, Zhongtian Ma, Qiaosheng Zhang, Zhen Wang, Xuelong Li

This paper considers the problem of community detection on multiple potentially correlated graphs from an information-theoretical perspective.

Community Detection Stochastic Block Model

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

1 code implementation17 Jan 2024 Hong Wang, Zhongkai Hao, Jie Wang, Zijie Geng, Zhen Wang, Bin Li, Feng Wu

To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.

Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms

no code implementations16 Jan 2024 Zhongtian Ma, Qiaosheng Zhang, Zhen Wang

Theoretical analyses show that our algorithm succeeds with high probability as long as the sample probability exceeds the aforementioned threshold, and this theoretical result is further validated by synthetic experiments.

Matrix Completion

Improving Graph Contrastive Learning via Adaptive Positive Sampling

no code implementations CVPR 2024 Jiaming Zhuo, Feiyang Qin, Can Cui, Kun fu, bingxin niu, Mengzhu Wang, Yuanfang Guo, Chuan Wang, Zhen Wang, Xiaochun Cao, Liang Yang

Graph Contrastive Learning (GCL) a Self-Supervised Learning (SSL) architecture tailored for graphs has shown notable potential for mitigating label scarcity.

Contrastive Learning Self-Supervised Learning

OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments

no code implementations19 Dec 2023 Jinyi Liu, Zhi Wang, Yan Zheng, Jianye Hao, Chenjia Bai, Junjie Ye, Zhen Wang, Haiyin Piao, Yang Sun

In reinforcement learning, the optimism in the face of uncertainty (OFU) is a mainstream principle for directing exploration towards less explored areas, characterized by higher uncertainty.

continuous-control Continuous Control +1

Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity

no code implementations18 Dec 2023 Zhihao Zhu, Chenwang Wu, Rui Fan, Yi Yang, Zhen Wang, Defu Lian, Enhong Chen

Recent research demonstrates that GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions.

Active Learning Diversity +2

Transferring CLIP's Knowledge into Zero-Shot Point Cloud Semantic Segmentation

no code implementations12 Dec 2023 Yuanbin Wang, Shaofei Huang, Yulu Gao, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Si Liu

In this work, we focus on zero-shot point cloud semantic segmentation and propose a simple yet effective baseline to transfer the visual-linguistic knowledge implied in CLIP to point cloud encoder at both feature and output levels.

3D Semantic Segmentation Point Cloud Segmentation +2

GAMC: An Unsupervised Method for Fake News Detection using Graph Autoencoder with Masking

1 code implementation10 Dec 2023 Shu Yin, Chao GAO, Zhen Wang

With the rise of social media, the spread of fake news has become a significant concern, potentially misleading public perceptions and impacting social stability.

Contrastive Learning Decoder +2

MVDD: Multi-View Depth Diffusion Models

no code implementations8 Dec 2023 Zhen Wang, Qiangeng Xu, Feitong Tan, Menglei Chai, Shichen Liu, Rohit Pandey, Sean Fanello, Achuta Kadambi, yinda zhang

State-of-the-art results from extensive experiments demonstrate MVDD's excellent ability in 3D shape generation, depth completion, and its potential as a 3D prior for downstream tasks.

3D Shape Generation Denoising +3

Control of the Power Flows of a Stochastic Power System

no code implementations27 Nov 2023 Zhen Wang, Kaihua Xi, Aijie Cheng, Hai Xiang Lin, Jan H. van Schuppen

How to determine the vector of power supplies of a stochastic power system for the next short horizon, such that the probability is less than a prespecified value that any phase-angle difference of a power line of the power network exits from a safe set?

DECap: Towards Generalized Explicit Caption Editing via Diffusion Mechanism

no code implementations25 Nov 2023 Zhen Wang, Xinyun Jiang, Jun Xiao, Tao Chen, Long Chen

The denoising process involves the explicit predictions of edit operations and corresponding content words, refining reference captions through iterative step-wise editing.

Caption Generation Denoising +1

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

2 code implementations5 Nov 2023 Zeren Chen, Ziqin Wang, Zhen Wang, Huayang Liu, Zhenfei Yin, Si Liu, Lu Sheng, Wanli Ouyang, Yu Qiao, Jing Shao

While this phenomenon has been overlooked in previous work, we propose a novel and extensible framework, called Octavius, for comprehensive studies and experimentation on multimodal learning with Multimodal Large Language Models (MLLMs).

Decoder Mixture-of-Experts +1

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

2 code implementations25 Oct 2023 Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P. Xing, Zhiting Hu

Highly effective, task-specific prompts are often heavily engineered by experts to integrate detailed instructions and domain insights based on a deep understanding of both instincts of large language models (LLMs) and the intricacies of the target task.

Navigate

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

1 code implementation11 Oct 2023 Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, DaCheng Tao

Plasticity, the ability of a neural network to evolve with new data, is crucial for high-performance and sample-efficient visual reinforcement learning (VRL).

Data Augmentation reinforcement-learning

Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness

1 code implementation29 Sep 2023 Xiaoyu Wen, Xudong Yu, Rui Yang, HaoYuan Chen, Chenjia Bai, Zhen Wang

Experimental results illustrate the superiority of RO2O in facilitating stable offline-to-online learning and achieving significant improvement with limited online interactions.

Offline RL reinforcement-learning +1

Node-Aligned Graph-to-Graph (NAG2G): Elevating Template-Free Deep Learning Approaches in Single-Step Retrosynthesis

1 code implementation27 Sep 2023 Lin Yao, Wentao Guo, Zhen Wang, Shang Xiang, Wentan Liu, Guolin Ke

Single-step retrosynthesis (SSR) in organic chemistry is increasingly benefiting from deep learning (DL) techniques in computer-aided synthesis design.

Benchmarking Graph Generation +3

LiON: Learning Point-wise Abstaining Penalty for LiDAR Outlier DetectioN Using Diverse Synthetic Data

2 code implementations19 Sep 2023 Shaocong Xu, Pengfei Li, Qianpu Sun, Xinyu Liu, Yang Li, Shihui Guo, Zhen Wang, Bo Jiang, Rui Wang, Kehua Sheng, Bo Zhang, Li Jiang, Hao Zhao, Yilun Chen

We demonstrate that learning different abstaining penalties, apart from point-wise penalty, for different types of (synthesized) outliers can further improve the performance.

Anomaly Detection Autonomous Driving +2

Least Squares Maximum and Weighted Generalization-Memorization Machines

no code implementations31 Aug 2023 Shuai Wang, Zhen Wang, Yuan-Hai Shao

Furthermore, we propose some different memory impact functions for the MIMM and WIMM.

Memorization

FashionLOGO: Prompting Multimodal Large Language Models for Fashion Logo Embeddings

1 code implementation17 Aug 2023 Zhen Wang, Da Li, Yulin Su, Min Yang, Minghui Qiu, Walton Wang

Instead, we view this as a multimodal task, using text as auxiliary information to facilitate the visual model's understanding of the logo.

Image Retrieval Logo Recognition +1

IOB: Integrating Optimization Transfer and Behavior Transfer for Multi-Policy Reuse

no code implementations14 Aug 2023 Siyuan Li, Hao Li, Jin Zhang, Zhen Wang, Peng Liu, Chongjie Zhang

Humans have the ability to reuse previously learned policies to solve new tasks quickly, and reinforcement learning (RL) agents can do the same by transferring knowledge from source policies to a related target task.

Continual Learning Reinforcement Learning (RL)

DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal

no code implementations28 Jul 2023 Ziyang Zhou, Yingtie Lei, Xuhang Chen, Shenghong Luo, Wenjun Zhang, Chi-Man Pun, Zhen Wang

Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability.

Document Shadow Removal

Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model

no code implementations17 Jul 2023 Rongke Liu, Dong Wang, Yizhi Ren, Zhen Wang, Kaitian Guo, Qianqian Qin, Xiaolei Liu

Therefore, the attack models in existing MIAs are difficult to effectively train with the knowledge of the target model, resulting in sub-optimal attacks.

model

Sequential Attention Source Identification Based on Feature Representation

no code implementations28 Jun 2023 Dongpeng Hou, Zhen Wang, Chao GAO, Xuelong Li

Snapshot observation based source localization has been widely studied due to its accessibility and low cost.

Decoder Graph Attention +1

MAT: Mixed-Strategy Game of Adversarial Training in Fine-tuning

no code implementations27 Jun 2023 Zhehua Zhong, Tianyi Chen, Zhen Wang

Fine-tuning large-scale pre-trained language models has been demonstrated effective for various natural language processing (NLP) tasks.

On the Value of Myopic Behavior in Policy Reuse

no code implementations28 May 2023 Kang Xu, Chenjia Bai, Shuang Qiu, Haoran He, Bin Zhao, Zhen Wang, Wei Li, Xuelong Li

Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.

Efficient Bilateral Cross-Modality Cluster Matching for Unsupervised Visible-Infrared Person ReID

no code implementations22 May 2023 De Cheng, Lingfeng He, Nannan Wang, Shizhou Zhang, Zhen Wang, Xinbo Gao

To this end, we propose a novel bilateral cluster matching-based learning framework to reduce the modality gap by matching cross-modality clusters.

Contrastive Learning Person Re-Identification

ReDirTrans: Latent-to-Latent Translation for Gaze and Head Redirection

no code implementations CVPR 2023 Shiwei Jin, Zhen Wang, Lei Wang, Ning Bi, Truong Nguyen

Then both the initial and edited embeddings are projected back (deprojected) to the initial latent space as residuals to modify the input latent vectors by subtraction and addition, representing old status removal and new status addition.

Attribute Gaze Estimation +2

Behavior Contrastive Learning for Unsupervised Skill Discovery

1 code implementation8 May 2023 Rushuai Yang, Chenjia Bai, Hongyi Guo, Siyuan Li, Bin Zhao, Zhen Wang, Peng Liu, Xuelong Li

Under mild assumptions, our objective maximizes the MI between different behaviors based on the same skill, which serves as an upper bound of the previous MI objective.

continuous-control Continuous Control +1

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

no code implementations4 May 2023 Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan

Furthermore, most methods concentrate on a single attack goal and lack a generalizable adversary to develop distinct attack strategies for diverse goals, thus limiting precise control over victim model behavior in real-world scenarios.

Specificity

Delving into Shape-aware Zero-shot Semantic Segmentation

1 code implementation CVPR 2023 Xinyu Liu, Beiwen Tian, Zhen Wang, Rui Wang, Kehua Sheng, Bo Zhang, Hao Zhao, Guyue Zhou

Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a surprisingly high accuracy.

Image Segmentation Segmentation +2

HPN: Personalized Federated Hyperparameter Optimization

no code implementations11 Apr 2023 Anda Cheng, Zhen Wang, Yaliang Li, Jian Cheng

The client encoding is calculated with a random projection-based procedure to protect each client's privacy.

Federated Learning Hyperparameter Optimization

GPT is becoming a Turing machine: Here are some ways to program it

no code implementations25 Mar 2023 Ana Jojic, Zhen Wang, Nebojsa Jojic

We demonstrate that, through appropriate prompting, GPT-3 family of models can be triggered to perform iterative behaviours necessary to execute (rather than just write or recall) programs that involve loops, including several popular algorithms found in computer science curricula or software developer interviews.

In-Context Learning

LON-GNN: Spectral GNNs with Learnable Orthonormal Basis

1 code implementation24 Mar 2023 Qian Tao, Zhen Wang, Wenyuan Yu, Yaliang Li, Zhewei Wei

In recent years, a plethora of spectral graph neural networks (GNN) methods have utilized polynomial basis with learnable coefficients to achieve top-tier performances on many node-level tasks.

Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

no code implementations6 Mar 2023 Zhen Wang, Rameswar Panda, Leonid Karlinsky, Rogerio Feris, Huan Sun, Yoon Kim

Prompt tuning, in which a base pretrained model is adapted to each task via conditioning on learned prompt vectors, has emerged as a promising approach for efficiently adapting large language models to multiple downstream tasks.

Transfer Learning

Exit options sustain altruistic punishment and decrease the second-order free-riders, but it is not a panacea

no code implementations12 Jan 2023 Chen Shen, Zhao Song, Lei Shi, Jun Tanimoto, Zhen Wang

Altruistic punishment, where individuals incur personal costs to punish others who have harmed third parties, presents an evolutionary conundrum as it undermines individual fitness.

Open-Ended Question Answering

Hard Sample Aware Network for Contrastive Deep Graph Clustering

2 code implementations16 Dec 2022 Yue Liu, Xihong Yang, Sihang Zhou, Xinwang Liu, Zhen Wang, Ke Liang, Wenxuan Tu, Liang Li, Jingcan Duan, Cancan Chen

Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.

Attribute Clustering +1

Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification

no code implementations30 Nov 2022 De Cheng, Haichun Tai, Nannan Wang, Zhen Wang, Xinbo Gao

In this paper, we propose a Neighbour Consistency guided Pseudo Label Refinement (NCPLR) framework, which can be regarded as a transductive form of label propagation under the assumption that the prediction of each example should be similar to its nearest neighbours'.

Clustering Person Retrieval +3

BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation

1 code implementation25 Nov 2022 Zhen Wang, Zheng Feng, Yanjun Li, Bowen Li, Yongrui Wang, Chulin Sha, Min He, Xiaolin Li

Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules.

Drug Discovery Molecular Property Prediction +4

Search to Pass Messages for Temporal Knowledge Graph Completion

1 code implementation30 Oct 2022 Zhen Wang, Haotong Du, Quanming Yao, Xuelong Li

In particular, we develop a generalized framework to explore topological and temporal information in TKGs.

Graph Neural Network Link Prediction +3

Entity Tracking via Effective Use of Multi-Task Learning Model and Mention-guided Decoding

2 code implementations12 Oct 2022 Janvijay Singh, Fan Bai, Zhen Wang

Cross-task knowledge transfer via multi-task learning has recently made remarkable progress in general NLP tasks.

Multi-Task Learning

A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learning

1 code implementation10 Oct 2022 Guozheng Ma, Zhen Wang, Zhecheng Yuan, Xueqian Wang, Bo Yuan, DaCheng Tao

Visual reinforcement learning (RL), which makes decisions directly from high-dimensional visual inputs, has demonstrated significant potential in various domains.

Data Augmentation reinforcement-learning +3

ThinkSum: Probabilistic reasoning over sets using large language models

no code implementations4 Oct 2022 Batu Ozturkler, Nikolay Malkin, Zhen Wang, Nebojsa Jojic

Our results suggest that because the probabilistic inference in ThinkSum is performed outside of calls to the LLM, ThinkSum is less sensitive to prompt design, yields more interpretable predictions, and can be flexibly combined with latent variable models to extract structured knowledge from LLMs.

In-Context Learning Retrieval

Cross Task Neural Architecture Search for EEG Signal Classifications

1 code implementation1 Oct 2022 Yiqun Duan, Zhen Wang, Yi Li, Jianhang Tang, Yu-Kai Wang, Chin-Teng Lin

Recently, various neural network approaches have been proposed to improve the accuracy of EEG signal recognition.

EEG Emotion Recognition +2

Hiding Visual Information via Obfuscating Adversarial Perturbations

1 code implementation ICCV 2023 Zhigang Su, Dawei Zhou, Nannan Wangu, Decheng Li, Zhen Wang, Xinbo Gao

Growing leakage and misuse of visual information raise security and privacy concerns, which promotes the development of information protection.

Adversarial Attack De-identification +1

Compressed Sensing Based RFI Mitigation and Restoration for Pulsar Signals

no code implementations The Astrophysical Journal 2022 Hao Shan, Jianping Yuan, Na Wang, Zhen Wang

In pulsar signal processing, two primary difficulties are (1) radio-frequency interference (RFI) mitigation and (2) information loss due to preprocessing and mitigation itself.

compressed sensing

A Game-Theoretic Perspective of Generalization in Reinforcement Learning

no code implementations7 Aug 2022 Chang Yang, Ruiyu Wang, Xinrun Wang, Zhen Wang

However, there is not a unified formulation of the various schemes, as well as the comprehensive comparisons of methods across different schemes.

Few-Shot Learning MuJoCo +4

Balancing Stability and Plasticity through Advanced Null Space in Continual Learning

no code implementations25 Jul 2022 Yajing Kong, Liu Liu, Zhen Wang, DaCheng Tao

Continual learning is a learning paradigm that learns tasks sequentially with resources constraints, in which the key challenge is stability-plasticity dilemma, i. e., it is uneasy to simultaneously have the stability to prevent catastrophic forgetting of old tasks and the plasticity to learn new tasks well.

Continual Learning

Online Continual Learning with Contrastive Vision Transformer

no code implementations24 Jul 2022 Zhen Wang, Liu Liu, Yajing Kong, Jiaxian Guo, DaCheng Tao

Based on the learnable focuses, we design a focal contrastive loss to rebalance contrastive learning between new and past classes and consolidate previously learned representations.

Continual Learning Contrastive Learning

Explicit Image Caption Editing

1 code implementation20 Jul 2022 Zhen Wang, Long Chen, Wenbo Ma, Guangxing Han, Yulei Niu, Jian Shao, Jun Xiao

Given an image and a reference caption, the image caption editing task aims to correct the misalignment errors and generate a refined caption.

Sentence

Bootstrapping a User-Centered Task-Oriented Dialogue System

no code implementations11 Jul 2022 Shijie Chen, Ziru Chen, Xiang Deng, Ashley Lewis, Lingbo Mo, Samuel Stevens, Zhen Wang, Xiang Yue, Tianshu Zhang, Yu Su, Huan Sun

We present TacoBot, a task-oriented dialogue system built for the inaugural Alexa Prize TaskBot Challenge, which assists users in completing multi-step cooking and home improvement tasks.

Data Augmentation Dialogue Management +2

Generalization-Memorization Machines

1 code implementation8 Jul 2022 Zhen Wang, Yuan-Hai Shao

Under this mechanism, error-based learning machines improve their memorization abilities of training data without over-fitting.

Memorization

Modern Question Answering Datasets and Benchmarks: A Survey

no code implementations30 Jun 2022 Zhen Wang

Question Answering (QA) is one of the most important natural language processing (NLP) tasks.

Deep Learning Question Answering +2

FedHPO-B: A Benchmark Suite for Federated Hyperparameter Optimization

1 code implementation8 Jun 2022 Zhen Wang, Weirui Kuang, Ce Zhang, Bolin Ding, Yaliang Li

Due to this uniqueness, existing HPO benchmarks no longer satisfy the need to compare HPO methods in the FL setting.

Benchmarking Federated Learning +1

A Benchmark for Federated Hetero-Task Learning

1 code implementation7 Jun 2022 Liuyi Yao, Dawei Gao, Zhen Wang, Yuexiang Xie, Weirui Kuang, Daoyuan Chen, Haohui Wang, Chenhe Dong, Bolin Ding, Yaliang Li

To investigate the heterogeneity in federated learning in real-world scenarios, we generalize the classic federated learning to federated hetero-task learning, which emphasizes the inconsistency across the participants in federated learning in terms of both data distribution and learning tasks.

Federated Learning Meta-Learning +2

EvenNet: Ignoring Odd-Hop Neighbors Improves Robustness of Graph Neural Networks

1 code implementation27 May 2022 Runlin Lei, Zhen Wang, Yaliang Li, Bolin Ding, Zhewei Wei

Despite their extraordinary predictive accuracy, existing approaches, such as GCN and GPRGNN, are not robust in the face of homophily changes on test graphs, rendering these models vulnerable to graph structural attacks and with limited capacity in generalizing to graphs of varied homophily levels.

Node Classification

D4: a Chinese Dialogue Dataset for Depression-Diagnosis-Oriented Chat

no code implementations24 May 2022 Binwei Yao, Chao Shi, Likai Zou, Lingfeng Dai, Mengyue Wu, Lu Chen, Zhen Wang, Kai Yu

In a depression-diagnosis-directed clinical session, doctors initiate a conversation with ample emotional support that guides the patients to expose their symptoms based on clinical diagnosis criteria.

Diagnostic Response Generation

PrEF: Percolation-based Evolutionary Framework for the diffusion-source-localization problem in large networks

no code implementations16 May 2022 Yang Liu, Xiaoqi Wang, Xi Wang, Zhen Wang, Jürgen Kurths

We assume that the state of a number of nodes in a network could be investigated if necessary, and study what configuration of those nodes could facilitate a better solution for the diffusion-source-localization (DSL) problem.

Towards Fine-grained Causal Reasoning and QA

1 code implementation15 Apr 2022 Linyi Yang, Zhen Wang, Yuxiang Wu, Jie Yang, Yue Zhang

Understanding causality is key to the success of NLP applications, especially in high-stakes domains.

Question Answering Sentence

FederatedScope-GNN: Towards a Unified, Comprehensive and Efficient Package for Federated Graph Learning

1 code implementation12 Apr 2022 Zhen Wang, Weirui Kuang, Yuexiang Xie, Liuyi Yao, Yaliang Li, Bolin Ding, Jingren Zhou

The incredible development of federated learning (FL) has benefited various tasks in the domains of computer vision and natural language processing, and the existing frameworks such as TFF and FATE has made the deployment easy in real-world applications.

Federated Learning Graph Learning

FederatedScope: A Flexible Federated Learning Platform for Heterogeneity

1 code implementation11 Apr 2022 Yuexiang Xie, Zhen Wang, Dawei Gao, Daoyuan Chen, Liuyi Yao, Weirui Kuang, Yaliang Li, Bolin Ding, Jingren Zhou

Although remarkable progress has been made by existing federated learning (FL) platforms to provide infrastructures for development, these platforms may not well tackle the challenges brought by various types of heterogeneity, including the heterogeneity in participants' local data, resources, behaviors and learning goals.

Federated Learning Hyperparameter Optimization

PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations

1 code implementation6 Apr 2022 Tong Sang, Hongyao Tang, Yi Ma, Jianye Hao, Yan Zheng, Zhaopeng Meng, Boyan Li, Zhen Wang

In online adaptation phase, with the environment context inferred from few experiences collected in new environments, the policy is optimized by gradient ascent with respect to the PDVF.

Contrastive Learning Decision Making +1

Experimental quantum adversarial learning with programmable superconducting qubits

no code implementations4 Apr 2022 Wenhui Ren, Weikang Li, Shibo Xu, Ke Wang, Wenjie Jiang, Feitong Jin, Xuhao Zhu, Jiachen Chen, Zixuan Song, Pengfei Zhang, Hang Dong, Xu Zhang, Jinfeng Deng, Yu Gao, Chuanyu Zhang, Yaozu Wu, Bing Zhang, Qiujiang Guo, Hekang Li, Zhen Wang, Jacob Biamonte, Chao Song, Dong-Ling Deng, H. Wang

Our results reveal experimentally a crucial vulnerability aspect of quantum learning systems under adversarial scenarios and demonstrate an effective defense strategy against adversarial attacks, which provide a valuable guide for quantum artificial intelligence applications with both near-term and future quantum devices.

BIG-bench Machine Learning Quantum Machine Learning

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

1 code implementation16 Mar 2022 Pengyi Li, Hongyao Tang, Tianpei Yang, Xiaotian Hao, Tong Sang, Yan Zheng, Jianye Hao, Matthew E. Taylor, Wenyuan Tao, Zhen Wang, Fazl Barez

However, we reveal sub-optimal collaborative behaviors also emerge with strong correlations, and simply maximizing the MI can, surprisingly, hinder the learning towards better collaboration.

Multi-agent Reinforcement Learning reinforcement-learning +1

Breaking the Curse of Dimensionality in Multiagent State Space: A Unified Agent Permutation Framework

no code implementations10 Mar 2022 Xiaotian Hao, Hangyu Mao, Weixun Wang, Yaodong Yang, Dong Li, Yan Zheng, Zhen Wang, Jianye Hao

To break this curse, we propose a unified agent permutation framework that exploits the permutation invariance (PI) and permutation equivariance (PE) inductive biases to reduce the multiagent state space.

Data Augmentation Reinforcement Learning (RL) +1

Regularized Bilinear Discriminant Analysis for Multivariate Time Series Data

no code implementations26 Feb 2022 Jianhua Zhao, Haiye Liang, Shulan Li, Zhiji Yang, Zhen Wang

To address the two problems, we propose RBLDA for MTS data classification, where each of the two within-class matrices is regularized via one parameter.

Model Selection Time Series +1

Adversarial Attacks and Defense Methods for Power Quality Recognition

1 code implementation11 Feb 2022 Jiwei Tian, Buhong Wang, Jing Li, Zhen Wang, Mete Ozay

To this end, we first propose a signal-specific method and a universal signal-agnostic method to attack power systems using generated adversarial examples.

Compactness Score: A Fast Filter Method for Unsupervised Feature Selection

no code implementations31 Jan 2022 Peican Zhu, Xin Hou, Keke Tang, Zhen Wang, Feiping Nie

For feature engineering, feature selection seems to be an important research content in which is anticipated to select "excellent" features from candidate ones.

Decision Making Dimensionality Reduction +2

MR-SVS: Singing Voice Synthesis with Multi-Reference Encoder

no code implementations11 Jan 2022 Shoutong Wang, Jinglin Liu, Yi Ren, Zhen Wang, Changliang Xu, Zhou Zhao

However, they face several challenges: 1) the fixed-size speaker embedding is not powerful enough to capture full details of the target timbre; 2) single reference audio does not contain sufficient timbre information of the target speaker; 3) the pitch inconsistency between different speakers also leads to a degradation in the generated voice.

Singing Voice Synthesis

Synthetic Generation of Face Videos With Plethysmograph Physiology

no code implementations CVPR 2022 Zhen Wang, Yunhao Ba, Pradyumna Chari, Oyku Deniz Bozkurt, Gianna Brown, Parth Patwa, Niranjan Vaddi, Laleh Jalilian, Achuta Kadambi

Accelerated by telemedicine, advances in Remote Photoplethysmography (rPPG) are beginning to offer a viable path toward non-contact physiological measurement.

Continual Learning With Lifelong Vision Transformer

no code implementations CVPR 2022 Zhen Wang, Liu Liu, Yiqun Duan, Yajing Kong, DaCheng Tao

Continual learning methods aim at training a neural network from sequential data with streaming labels, relieving catastrophic forgetting.

Continual Learning

ED2: Environment Dynamics Decomposition World Models for Continuous Control

1 code implementation6 Dec 2021 Jianye Hao, Yifu Yuan, Cong Wang, Zhen Wang

Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error.

continuous-control Continuous Control +1

Understanding the Dynamics of DNNs Using Graph Modularity

1 code implementation24 Nov 2021 Yao Lu, Wen Yang, Yunzhe Zhang, Zuohui Chen, Jinyin Chen, Qi Xuan, Zhen Wang, Xiaoniu Yang

Specifically, we model the process of class separation of intermediate representations in pre-trained DNNs as the evolution of communities in dynamic graphs.

Feature Engineering

Graph-Based Similarity of Neural Network Representations

1 code implementation22 Nov 2021 Zuohui Chen, Yao Lu, Jinxuan Hu, Wen Yang, Qi Xuan, Zhen Wang, Xiaoniu Yang

Understanding the black-box representations in Deep Neural Networks (DNN) is an essential problem in deep learning.

Coarformer: Transformer for large graph via graph coarsening

no code implementations29 Sep 2021 Weirui Kuang, Zhen Wang, Yaliang Li, Zhewei Wei, Bolin Ding

We get rid of these obstacles by exploiting the complementary natures of GNN and Transformer, and trade the fine-grained long-range information for the efficiency of Transformer.

iFlood: A Stable and Effective Regularizer

no code implementations ICLR 2022 Yuexiang Xie, Zhen Wang, Yaliang Li, Ce Zhang, Jingren Zhou, Bolin Ding

However, our further studies uncover that the design of the loss function of Flooding can lead to a discrepancy between its objective and implementation, and cause the instability issue.

image-classification Image Classification

Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain

no code implementations14 Sep 2021 Jianye Hao, Tianpei Yang, Hongyao Tang, Chenjia Bai, Jinyi Liu, Zhaopeng Meng, Peng Liu, Zhen Wang

In addition to algorithmic analysis, we provide a comprehensive and unified empirical comparison of different exploration methods for DRL on a set of commonly used benchmarks.

Autonomous Vehicles Deep Reinforcement Learning +5

N24News: A New Dataset for Multimodal News Classification

1 code implementation LREC 2022 Zhen Wang, Xu Shan, Xiangxie Zhang, Jie Yang

Current news datasets merely focus on text features on the news and rarely leverage the feature of images, excluding numerous essential features for news classification.

Classification +1

Synchronization of Power Systems under Stochastic Disturbances

no code implementations9 Aug 2021 Zhen Wang, Kaihua Xi, Aijie Cheng, Hai Xiang Lin, André C. M. Ran, Jan H. van Schuppen, Chenghui Zhang

The synchronization of power generators is an important condition for the proper functioning of a power system, in which the fluctuations in frequency and the phase angle differences between the generators are sufficiently small when subjected to stochastic disturbances.

Overcoming Difficulty in Obtaining Dark-skinned Subjects for Remote-PPG by Synthetic Augmentation

no code implementations10 Jun 2021 Yunhao Ba, Zhen Wang, Kerim Doruk Karinca, Oyku Deniz Bozkurt, Achuta Kadambi

Camera-based remote photoplethysmography (rPPG) provides a non-contact way to measure physiological signals (e. g., heart rate) using facial videos.

Diversity

Chinese Sentences Similarity via Cross-Attention Based Siamese Network

no code implementations18 Apr 2021 Zhen Wang, Xiangxie Zhang, Yicong Tan

Measuring sentence similarity is a key research area nowadays as it allows machines to better understand human languages.

Sentence Sentence Similarity

Fuzzy Discriminant Clustering with Fuzzy Pairwise Constraints

1 code implementation17 Apr 2021 Zhen Wang, Shan-Shan Wang, Lan Bai, Wen-Si Wang, Yuan-Hai Shao

In semi-supervised fuzzy clustering, this paper extends the traditional pairwise constraint (i. e., must-link or cannot-link) to fuzzy pairwise constraint.

Clustering

Equilibrium and Socially optimal of a double-sided queueing system with two-mass point matching time

no code implementations28 Jan 2021 Zhen Wang, Cheryl Yang, Liwei Liu, Yiqiang Q. Zhao

The numerical scenarios illustrate the influence of parameters on the equilibrium strategy and socially optimal strategy under two information levels.

Probability 60K25, 91B50, 91A35

Ensemble and Random Collaborative Representation-Based Anomaly Detector for Hyperspectral Imagery

no code implementations6 Jan 2021 Rong Wang, Yihang Lu, Qianrong Zhang, Feiping Nie, Zhen Wang, Xuelong Li

To alleviate this problem, we proposed a novel ensemble and random collaborative representation-based detector (ERCRD) for HAD, which comprises two closely related stages.

Anomaly Detection Ensemble Learning

Semantic Inference Network for Few-shot Streaming Label Learning

no code implementations1 Jan 2021 Zhen Wang, Liu Liu, Yiqun Duan, DaCheng Tao

In this work, we formulate and study few-shot streaming label learning (FSLL), which models emerging new labels with only a few annotated examples by utilizing the knowledge learned from past labels.

Meta-Learning Multi-Label Classification +1

ROBY: Evaluating the Robustness of a Deep Model by its Decision Boundaries

no code implementations18 Dec 2020 Jinyin Chen, Zhen Wang, Haibin Zheng, Jun Xiao, Zhaoyan Ming

This work proposes a generic evaluation metric ROBY, a novel attack-independent robustness measure based on the model's decision boundaries.

EvaLDA: Efficient Evasion Attacks Towards Latent Dirichlet Allocation

1 code implementation9 Dec 2020 Qi Zhou, Haipeng Chen, Yitao Zheng, Zhen Wang

As one of the most powerful topic models, Latent Dirichlet Allocation (LDA) has been used in a vast range of tasks, including document understanding, information retrieval and peer-reviewer assignment.

document understanding Information Retrieval +3

Method and Dataset Entity Mining in Scientific Literature: A CNN + Bi-LSTM Model with Self-attention

no code implementations26 Oct 2020 Linlin Hou, Ji Zhang, Ou wu, Ting Yu, Zhen Wang, Zhao Li, Jianliang Gao, Yingchun Ye, Rujing Yao

We finally apply our model on PAKDD papers published from 2009-2019 to mine insightful results from scientific papers published in a longer time span.

Data Augmentation

Exercise Hierarchical Feature Enhanced Knowledge Tracing

no code implementations23 Oct 2020 Hanshuang Tong, Yun Zhou, Zhen Wang

Knowledge tracing is a fundamental task in the computer-aid educational system.

Knowledge Tracing

Exploring Common and Individual Characteristics of Students via Matrix Recovering

no code implementations23 Oct 2020 Zhen Wang, Ben Teng, Yun Zhou, Hanshuang Tong, Guangtong Liu

We assume that the characteristics matrix of students' is composed of two parts: one is a low-rank matrix representing the common characteristics of students; the other is a sparse matrix representing individual characteristics of students.

Unseen Target Stance Detection with Adversarial Domain Generalization

1 code implementation12 Oct 2020 Zhen Wang, Qiansheng Wang, Chengguo Lv, Xue Cao, Guohong Fu

Although stance detection has made great progress in the past few years, it is still facing the problem of unseen targets.

Domain Generalization Stance Detection

Cue-word Driven Neural Response Generation with a Shrinking Vocabulary

1 code implementation10 Oct 2020 Qiansheng Wang, Yuxin Liu, Chengguo Lv, Zhen Wang, Guohong Fu

Open-domain response generation is the task of generating sensible and informative re-sponses to the source sentence.

Response Generation Sentence

FIVES: Feature Interaction Via Edge Search for Large-Scale Tabular Data

no code implementations29 Jul 2020 Yuexiang Xie, Zhen Wang, Yaliang Li, Bolin Ding, Nezihe Merve Gürel, Ce Zhang, Minlie Huang, Wei. Lin, Jingren Zhou

Then we instantiate this search strategy by optimizing both a dedicated graph neural network (GNN) and the adjacency tensor associated with the defined feature graph.

Graph Neural Network

HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing

no code implementations13 Jun 2020 Hanshuang Tong, Zhen Wang, Yun Zhou, Shiwei Tong, Wenyuan Han, Qi Liu

To solve the above problems, we propose a hierarchical graph knowledge tracing model called HGKT to explore the latent hierarchical relations between exercises.

Knowledge Tracing

Rationalizing Medical Relation Prediction from Corpus-level Statistics

1 code implementation ACL 2020 Zhen Wang, Jennifer Lee, Simon Lin, Huan Sun

Nowadays, the interpretability of machine learning models is becoming increasingly important, especially in the medical domain.

Decision Making Prediction +2

A Semi-supervised Graph Attentive Network for Financial Fraud Detection

1 code implementation28 Feb 2020 Daixin Wang, Jianbin Lin, Peng Cui, Quanhui Jia, Zhen Wang, Yanming Fang, Quan Yu, Jun Zhou, Shuang Yang, Yuan Qi

Additionally, among the network, only very few of the users are labelled, which also poses a great challenge for only utilizing labeled data to achieve a satisfied performance on fraud detection.

Fraud Detection Graph Neural Network

Tree++: Truncated Tree Based Graph Kernels

1 code implementation23 Feb 2020 Wei Ye, Zhen Wang, Rachel Redberg, Ambuj Singh

At the heart of Tree++ is a graph kernel called the path-pattern graph kernel.

Graph Similarity

Multiple Flat Projections for Cross-manifold Clustering

no code implementations17 Feb 2020 Lan Bai, Yuan-Hai Shao, Wei-Jie Chen, Zhen Wang, Nai-Yang Deng

In this paper, we propose a Multiple Flat Projections Clustering (MFPC) to deal with cross-manifold clustering problems.

Clustering

Texture Classification using Block Intensity and Gradient Difference (BIGD) Descriptor

no code implementations4 Feb 2020 Yuting Hu, Zhen Wang, Ghassan AlRegib

In this paper, we present an efficient and distinctive local descriptor, namely block intensity and gradient difference (BIGD).

Classification General Classification +1

AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Search

1 code implementation13 Jan 2020 Daoyuan Chen, Yaliang Li, Minghui Qiu, Zhen Wang, Bofang Li, Bolin Ding, Hongbo Deng, Jun Huang, Wei. Lin, Jingren Zhou

Motivated by the necessity and benefits of task-oriented BERT compression, we propose a novel compression method, AdaBERT, that leverages differentiable Neural Architecture Search to automatically compress BERT into task-adaptive small models for specific tasks.

Knowledge Distillation Neural Architecture Search

Learning to Answer Subjective, Specific Product-Related Queries using Customer Reviews by Adversarial Domain Adaptation

no code implementations18 Oct 2019 Manirupa Das, Zhen Wang, Evan Jaffe, Madhuja Chattopadhyay, Eric Fosler-Lussier, Rajiv Ramnath

Online customer reviews on large-scale e-commerce websites, represent a rich and varied source of opinion data, often providing subjective qualitative assessments of product usage that can help potential customers to discover features that meet their personal needs and preferences.

Domain Adaptation Sentence

A Distributed Fair Machine Learning Framework with Private Demographic Data Protection

1 code implementation17 Sep 2019 Hui Hu, Yijun Liu, Zhen Wang, Chao Lan

In this paper, we propose a distributed fair learning framework for protecting the privacy of demographic data.

BIG-bench Machine Learning Fairness

SurfCon: Synonym Discovery on Privacy-Aware Clinical Data

1 code implementation21 Jun 2019 Zhen Wang, Xiang Yue, Soheil Moosavinasab, Yungui Huang, Simon Lin, Huan Sun

To solve the problem, we propose a new framework SurfCon that leverages two important types of information in the privacy-aware clinical data, i. e., the surface form information, and the global context information for synonym discovery.

Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations

4 code implementations12 Jun 2019 Xiang Yue, Zhen Wang, Jingong Huang, Srinivasan Parthasarathy, Soheil Moosavinasab, Yungui Huang, Simon M. Lin, Wen Zhang, Ping Zhang, Huan Sun

Our experimental results demonstrate that the recent graph embedding methods achieve promising results and deserve more attention in the future biomedical graph analysis.

Graph Embedding Link Prediction +3

Fisher-Bures Adversary Graph Convolutional Networks

1 code implementation11 Mar 2019 Ke Sun, Piotr Koniusz, Zhen Wang

We try to minimize the loss wrt the perturbed $G+\Delta{G}$ while making $\Delta{G}$ to be effective in terms of the Fisher information of the neural network.

Graph Neural Network Node Classification

Characterization of migrated seismic volumes using texture attributes: a comparative study

no code implementations30 Jan 2019 Zhiling Long, Yazeed Alaudah, Muhammad Ali Qureshi, Motaz Al Farraj, Zhen Wang, Asjad Amin, Mohamed Deriche, Ghassan AlRegib

It is our hope that this comparative study will help acquaint the seismic interpretation community with the many available powerful image texture analysis techniques, providing more alternative attributes for their seismic exploration.

Image Retrieval Retrieval +2

Ramp-based Twin Support Vector Clustering

no code implementations10 Dec 2018 Zhen Wang, Xu Chen, Chun-Na Li, Yuan-Hai Shao

Traditional plane-based clustering methods measure the cost of within-cluster and between-cluster by quadratic, linear or some other unbounded functions, which may amplify the impact of cost.

Clustering

Robust Bhattacharyya bound linear discriminant analysis through adaptive algorithm

no code implementations6 Nov 2018 Chun-Na Li, Yuan-Hai Shao, Zhen Wang, Nai-Yang Deng

In this paper, we propose a novel linear discriminant analysis criterion via the Bhattacharyya error bound estimation based on a novel L1-norm (L1BLDA) and L2-norm (L2BLDA).

Joint Training of Candidate Extraction and Answer Selection for Reading Comprehension

no code implementations ACL 2018 Zhen Wang, Jiachen Liu, Xinyan Xiao, Yajuan Lyu, Tian Wu

While sophisticated neural-based techniques have been developed in reading comprehension, most approaches model the answer in an independent manner, ignoring its relations with other answer candidates.

Answer Selection Reading Comprehension +1

A Many-Objective Evolutionary Algorithm With Two Interacting Processes: Cascade Clustering and Reference Point Incremental Learning

no code implementations3 Mar 2018 Hongwei Ge, Mingde Zhao, Liang Sun, Zhen Wang, Guozhen Tan, Qiang Zhang, C. L. Philip Chen

This paper proposes a many-objective optimization algorithm with two interacting processes: cascade clustering and reference point incremental learning (CLIA).

Clustering Diversity +1

On the Effectiveness of Least Squares Generative Adversarial Networks

3 code implementations18 Dec 2017 Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang, Stephen Paul Smolley

To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss for both the discriminator and the generator.

Insensitive Stochastic Gradient Twin Support Vector Machine for Large Scale Problems

no code implementations19 Apr 2017 Zhen Wang, Yuan-Hai Shao, Lan Bai, Li-Ming Liu, Nai-Yang Deng

In this paper, stochastic gradient descent algorithm is investigated to twin support vector machines for classification.

General Classification

Least Squares Generative Adversarial Networks

24 code implementations ICCV 2017 Xudong Mao, Qing Li, Haoran Xie, Raymond Y. K. Lau, Zhen Wang, Stephen Paul Smolley

To overcome such a problem, we propose in this paper the Least Squares Generative Adversarial Networks (LSGANs) which adopt the least squares loss function for the discriminator.

Cannot find the paper you are looking for? You can Submit a new open access paper.