X. Wang
profile photo

Xiangfeng Wang

I am an associate professor at School of Computer Science and Technology, East China Normal University. Before that, I received my Bachelor degree and PhD degree from Nanjing University in 2009 and 2014 respectively under the supervision of Professor Bingsheng He. During my PhD study, I was supported by the National Scholarship Council for joint PhD at the University of Minnesota under the supervision of Professor Zhi-Quan Luo. I was awarded the 2022 Shanghai QiMingXing Project and the 2021 IEEE Signal Processing Society Best Paper Award.

Email  /  Google Scholar

Research Areas

  • Multi-agent Learning and Distributed Optimization

  • Learn to Optimize: continuous or distributed cases

  • Trustworthy Machine Learning: fairness, privacy and etc.
  • Recent Projects

  • VMAgent
  • Project Page

    VMAgent is a platform for exploiting Reinforcement Learning (RL) on Virtual Machine (VM) scheduling tasks. It is developed by the Multi-Agent Artificial Intelligence Lab (MAIL) in East China Normal University and Algorithm Innovation Lab in HUAWEI Cloud. VMAgent is constructed based on one month real VM scheduling dataset called Huawei-East-1 from HUAWEI Cloud and it contains multiple practicle VM scheduling scenarios (such as Fading, Rcovering, etc). These scenarios also correspond to the challanges in the RL. Exploiting the design of RL methods in these secenarios help both the RL and VM scheduling communities. To emphasis, more details about VMAgent can be found in our paper VMAgent: A Practical Virtual Machine Scheduling Platform. Our another paper Learning to Schedule Multi-NUMA Virtual Machines via Reinforcement Learning has employed this VMAgent simultor to design RL-based VM scheduling algorithms.

    Research

    Journal Papers:

    1. Structured Cooperative Reinforcement Learning with Time-varying Composite Action Space
      Wenhao Li, Xiangfeng Wang, Bo Jin, Dixin Luo, and Hongyuan Zha
      IEEE Transactions on Pattern Analysis and Machine Intelligence 2022 | paper

    2. Perturbation Techniques for Convergence Analysis of Proximal Gradient Method and Other First-order Algorithms via Variational Analysis
      Xiangfeng Wang, Jane J. Ye, Xiaoming Yuan, Shangzhi Zeng, and Jin Zhang
      Set-Valued and Variational Analysis 2022 | paper

    3. Learning to Schedule Multi-NUMA Virtual Machines via Reinforcement Learning
      Junjie Sheng, Yiqiu Hu, Wenli Zhou, Lei Zhu, Bo Jin, Jun Wang, and Xiangfeng Wang
      Pattern Recognition 2022 | paper

    4. The O(1/n) Worst-case Convergence Rate of ADMM with Variable Penalty Parameters
      Xingju Cai, Xiangfeng Wang, and Wenxing Zhang
      Numerical Mathematics A Journal of Chinese Universities 2021 | Commemorate the 100th anniversary of the birth of Professor Xuchu He

    5. Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning
      Chaofan Ma, Qisen Xu, Xiangfeng Wang, Bo Jin, Xiaoyu Zhang, Yanfeng Wang, and Ya Zhang
      IEEE Transactions on Medical Imaging 2021 | paper

    6. Distributed and Parallel ADMM for Structured Nonconvex Optimization Problem
      Xiangfeng Wang, Junchi Yan, Bo Jin, and Wwenhao Li
      IEEE Transactions on Cybernetics 2021 | paper

    7. Survey on Fairness in Trustworthy Machine Learning
      Wenyan Liu, Chuyun Shen, Xiangfeng Wang, Bo Jin, Xingjian Lu, Xiangfeng Wang, Hongyuan Zha, and Jifeng He
      Journal of Software 2021 | paper

    8. The Distance Between Convex Sets with Minkowski Sum Structure: Application to Collision Detection
      Xiangfeng Wang, Junping Zhang, and Wenxing Zhang
      Computational Optimization and Applications 2020 | paper

    9. A Block Successive Upper Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization
      Mingyi Hong, Tsung-Hui Chang, Xiangfeng Wang, Meisam Razaviyayn, Shiqian Ma, and Zhi-Quan Luo
      Mathematics of Operations Research 2020 | paper

    10. Joint Active Learning with Feature Selection via CUR Matrix Decomposition
      Changsheng Li, Xiangfeng Wang, Weishan Dong, Junchi Yan, Qingshan Liu, and Hongyuan Zha
      IEEE Transactions on Pattern Analysis and Machine Intelligence 2019 | paper

    11. Dynamic Structure Embedded Online Multiple-Output Regression for Streaming Data
      Changsheng Li, Fan Wei, Weishan Dong, Xiangfeng Wang, Qingshan Liu, and Xin Zhang
      IEEE Transactions on Pattern Analysis and Machine Intelligence 2019 | paper

    12. Implementing the ADMM to Big Datasets: A Case Study of LASSO
      Hangrui Yue, Qingzhi Yang, Xiangfeng Wang, and Xiaoming Yuan
      SIAM Journal on Scientific Computing 2018 | paper

    13. On the Flexibility of Block Coordinate Descent for Large-Scale Optimization
      Xiangfeng Wang, Wenjie Zhang, Junchi Yan, Xiaoming Yuan, and Hongyuan Zha
      Neurocomputing 2018 | paper

    14. Iteration Complexity Analysis of Block Coordinate Descent Methods
      Mingyi Hong, Xiangfeng Wang, Meisam Razaviyayn, and Zhi-Quan Luo
      Mathematical Programming 2017 | paper

    15. Asynchronous Distributed ADMM for Large-Scale Optimization-Part I: Algorithm and Convergence Analysis
      Tsung-Hui Chang, Mingyi Hong, Wei-Cheng Liao, and Xiangfeng Wang
      IEEE Transactions on Signal Processing 2016 | paper

    16. Asynchronous Distributed ADMM for Large-Scale Optimization-Part II: Linear Convergence Analysis and Numerical Performances
      Tsung-Hui Chang, Wei-Cheng Liao, Mingyi Hong, and Xiangfeng Wang
      IEEE Transactions on Signal Processing 2016 | paper

    17. On the Convergence Rate of a Class of Proximal-Based Decomposition Methods for Monotone Variational Inequalities
      Xiangfeng Wang
      Journal of the Operations Research Society of China 2015 | paper

    18. Solving Multiple-Block Separable Convex Minimization Problems using Two-Block ADMM
      Xiangfeng Wang, Mingyi Hong, Shiqian Ma, and Zhi-Quan Luo
      Pacific Journal of Optimization 2015 | paper

    19. Multi-Agent Distributed Large-Scale Optimization by Inexact Consensus ADMM
      Tsung-Hui Chang, Mingyi Hong, and Xiangfeng Wang
      IEEE Transactions on Signal Processing 2015 | paper | IEEE Signal Processing Society Best Paper Award

    20. Efficient InSAR Phase Noise Reduction via Total Variation Regularization
      Xiaomei Luo, Xiangfeng Wang, Zhiyong Suo, and Zhenfang Li
      Science China (Information Sciences) 2015 | paper

    21. The Linearized Alternating Direction Method of Multipliers for Dantzig Selector
      Xiangfeng Wang, and Xiaoming Yuan
      SIAM Journal of Scientific Computing 2012 | paper

    Conference Papers:

    1. VMAgent: A Practical Virtual Machine Scheduling Platform
      Junjie Sheng, Shengliang Cai, Haochuan Cui, Wenhao Li, Yun Hua, Bo Jin, Wenli Zhou, Yiqiu Hu, Lei Zhu, Qian Peng, Hongyuan Zha, and Xiangfeng Wang
      IJCAI 2022 | paper | The VMAgent Simulator

    2. Multi-Agent Path Finding with Prioritized Communication Learning
      Wenhao Li, Hongjun Chen, Bo Jin, Wenzhe Tan, Hongyuan Zha, and Xiangfeng Wang
      ICRA 2022 | paper

    3. Weighted Mean-Field Multi-Agent Reinforcement Learning via Reward Attribution Decomposition
      Tingyu Wu, Wenhao Li, Bo Jin, Wei Zhang, and Xiangfeng Wang
      DASFAA 2022 | paper

    4. Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition
      Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, and Hongyuan Zha
      ICLR 2022 | paper

    5. HMRL: Hyper-Meta Learning for Sparse Reward Reinforcement Learning Problem
      Yun Hua, Xiangfeng Wang, Bo Jin, Wenhao Li, Junchi Yan, Xiaofeng He, and Hongyuan Zha
      KDD 2021 | paper

    6. Semi-supervised Medical Image Segmentation with Confidence Calibration
      Qisen Xu, Qian Wu, Yiqiu Hu, Bo Jin, Bin Hu, Fengping Zhu, Yuxin Li, and Xiangfeng Wang
      IJCNN 2021 | paper

    7. Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning
      Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng, Yun Hua, and Hongyuan Zha
      AAMAS 2021 | paper

    8. VSB$^2$-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing
      Xin Li, Xiangfeng Wang, Bo Jin, Wenjie Zhang, Junjie Wang, and Hongyuan Zha
      ICPR 2020 | paper

    9. Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning
      Junjie Wang, Xiangfeng Wang, Bo Jin, Junchi Yan, Wenjie Zhang, and Hongyuan Zha
      ICPR 2020 | paper

    10. Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning
      Xuan Liao, Wenhao Li, Qisen Xu, Xiangfeng Wang, Bo Jin, Xiaoyun Zhang, Ya Zhang, and Yanfeng Wang
      CVPR 2020 | paper

    11. Visual-to-Semantic Hashing for Zero-shot Learning
      Xin Li, Xiaoyue Wen, Bo Jin, Xiangfeng Wang, Junjie Wang, and Jinghui Cai
      IJCNN 2020 | paper

    12. A Fast Proximal Point Method for Computing Exact Wasserstein Distance
      Yujia Xie, Xiangfeng Wang, Ruijia Wang, and Hongyuan Zha
      UAI 2019 | paper

    13. SparseMAAC: Sparse Attention for Multi-agent Reinforcement Learning
      Wenhao Li, Bo Jin, and Xiangfeng Wang
      DASFAA 2019 | paper

    14. Deep eXtreme Multi-label Learning
      Wenjie Zhang, Junchi Yan, Xiangfeng Wang, and Hongyuan Zha
      ICMR 2018 | paper

    15. Joint Day-Ahead Power Procurement and Load Scheduling using Stochastic ADMM
      Xiangfeng Wang, Mingyi Hong, Tsung-Hui Chang, Meisam Razaviyayn, and Zhi-Quan Luo
      ICASSP 2014 | paper

    Books and Book Chapters:

    1. 群体智能/Swarm Intelligence(人工智能与智能教育丛书)
      Xiangfeng Wang, and Bo Jin
      教育科学出版社 2021

    2. 人机协同/Human-Machine Synergy
      Xindong Wu, Xiangfeng Wang, Bo Jin, Zheng Yu, and Minghui Wu
      科学出版社 2022

    3. 人工智能伦理与安全(第4章-安全可信人工智能)
      Xiaoling Wang, Xiangfeng Wang, and Bo Jin
      清华大学出版社 2022

    4. Block-wise Alternating Direction Method of Multipliers with Gaussian Back Substitution for Multiple-block Convex Programming
      Xiaoling Fu, Bingsheng He, Xiangfeng Wang, and Xiaoming Yuan
      Splitting Algorithms, Modern Operator Theory, and Applications 2019 | chapter

    Awards

  • 2022, Shanghai QiMingXing

  • 2021, IEEE Signal Processing Society Best Paper Award
  • Welcome to use this website's source code, just add a link back to here.
    No. Visitor Since Feb 2022. Powered by w3.css