Multi-Agent Artificial Intelligence Laboratory

Multi-Agent Artificial Intelligence Laboratory

East China Normal University

Xiangfeng WANG

Xiangfeng Wang

Personal Information

  • Associate Professor
  • School of Computer Science and Technology, East China Normal University
  • Email: xfwang at cs.ecnu.edu.cn

Education

  • Ph.D., Computational Mathematics/Optimization, Nanjing Univerisity, 2014 (Supervisor: Professor Bingsheng He)
  • Visiting Ph.D. student, Optimization, University of Minnesota, 2012-2013 (Supervisor: Professor Zhi-Quan Luo)
  • B.S., Mathematics, Nanjing University, 2009

Academic Employment

  • 2018-now, Associate Professor, School of Computer Science and Technology, East China Normal University
  • 2014-2018, Assistant Professor, School of Computer Science and Technology, East China Normal University

Research Area

  • Distributed Optimization and Applications
  • Multi-agent Learning
  • Trustworthy Machine Learning: Fairness, Privacy, etc.

Awards

  • 2021 IEEE Signal Processing Society Best Paper Award (for the paper Multi-Agent Distributed Large-Scale Optimization by Inexact Consensus ADMM with Tsung-Hui Chang and Mingyi Hong on IEEE Transactions on Signal Processing)
  • 2022 Shanghai QiMingXing

Externally Funded Projects

  • Model-driven Real-time Control Platform based on ML-driven ODE Solver, QiMingXing Project of Shanghai, STCSM, 2022-2025.
  • Research on Advanced Machine Learning Method based on Structured Self-Adaptive and Self-Evolution, National Key Research and Development Program of China, MOST, 2021-2023.
  • Research on Machine Learning Algorithms for Distributed Optimization Problems, National Natural Science Foundations of China, NSFC, 2021-2024.
  • Research on Trustworthy Machine Learning, Artificial Intelligence Project of Shanghai, STCSM, 2021-2022.
  • Virtual Scheduling Algorithm based on Reinforcement Learning, Huawei Project, 2020-2021.
  • Distributed Optimization-driven Multi-agent Collaborative Computing Theory and Method, ZhiJiang Project, 2020-2022.
  • Research on Structured Algorithm for Large-scale Optimization Problem in Machine Learning, Natural Science Foundation of Shanghai, STCSM, 2019-2022.
  • Research on Structured First-order Algorithm for Large-scale Distributed Consensus Optimization Problem, National Natural Science Foundations of China, NSFC, 2016-2018.
  • Research on Large-scale Distributed Stochastic Optimization Algorithm, YangFan Project of Shanghai, STCSM, 2015-2017.
  • Remark: MOST (Ministry of Science and Technology of the People’s Republic of China); NSFC (Natural Science Foundations of China); STCSM (Science and Technology Commission of Shanghai Municipality).

Publications

Book and Book Chapter

  1. 王祥丰/金博, 群体智能/Swarm Intelligence, 人工智能与智能教育丛书, 教育科学出版社.
  2. 吴信东/王祥丰/金博/于政/吴明辉，人机协同/Human-Machine Synergy，科学出版社.
  3. 王晓玲/王祥丰/金博，人工智能伦理与安全(第4章-安全可信人工智能)，清华大学出版社.
  4. X. Fu, B. He, Xiangfeng Wang, and X. Yuan, Block-wise Alternating Direction Method of Multipliers with Gaussian Back Substitution for Multiple-block Convex Programming. Splitting Algorithms, Modern Operator Theory, and Applications, 2019.

Journal

  1. W. Li, Xiangfeng Wang, B. Jin, D. Luo, and H. Zha, Structured Cooperative Reinforcement Learning with Time-varying Composite Action Space. IEEE Transactions on Pattern Analysis and Machine Intelligence, accepted, 2021.
  2. Xiangfeng Wang, J. Ye, X. Yuan, S. Zeng, and J. Zhang, Perturbation Techniques for Convergence Analysis of Proximal Gradient Method and Other First-order Algorithms via Variational Analysis. Set-Valued and Variational Analysis, 30, 2022, pp.39-79.
  3. J. Sheng, Y. Hu, W. Zhou, L. Zhu, B. Jin, J. Wang, and Xiangfeng Wang, Learning to Schedule Multi-NUMA Virtual Machines via Reinforcement Learning. Pattern Recognition, 121, 2022, pp.108254.
  4. X. Cai, Xiangfeng Wang, and W. Zhang, The O(1/n) Worst-case Convergence Rate of ADMM with Variable Penalty Parameters. Numerical Mathematics A Journal of Chinese Universities, 43(04), 2021, pp.317-334. (Commemorate the 100th anniversary of the birth of Professor Xuchu He)
  5. C. Ma, Q. Xu, Xiangfeng Wang, Bo Jin, X. Zhang, Y. Wang, and Y. Zhang, Boundary-aware Supervoxel-level Iteratively Refined Interactive 3D Image Segmentation with Multi-agent Reinforcement Learning. IEEE Transactions on Medical Imaging, 40(10), 2021, pp.2563-2574.
  6. Xiangfeng Wang, J. Yan, B. Jin, and W. Li, Distributed and Parallel ADMM for Structured Nonconvex Optimization Problem. IEEE Transactions on Cybernetics, 51(9), 2021, pp.4540-4552.
  7. Y. Song, T. Liu, T. Wei, Xiangfeng Wang, Z. Tao, and M. Chen, FDA3: Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications. IEEE Transactions on Industrial Informatics, 17(11), 2021, pp.7830-7838.
  8. W. Liu, C. Shen, Xiangfeng Wang, B. Jin, X. Lu, X. Wang, H. Zha, and J. He, Fairness in Trustworthy Machine Learning: A Survey. Journal of Software, 32(5), 2021, pp.1404-1426. (Chinese version)
  9. Xiangfeng Wang, J. Zhang, and W. Zhang, The Distance Between Convex Sets with Minkowski Sum Structure: Application to Collision Detection. Computational Optimization and Applications, 77, 2020, pp.465–490.
  10. M. Hong, T.-H. Chang, Xiangfeng Wang, M. Razaviyayn, S. Ma, and Z.-Q. Luo, A Block Successive Upper Bound Minimization Method of Multipliers for Linearly Constrained Convex Optimization. Mathematics of Operations Research, 45(3), 2020, pp.833-861.
  11. C. Li, Xiangfeng Wang, W. Dong, J. Yan, Q. Liu, and H. Zha, Active Sample Learning and Feature Selection: A Unified Approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(6), 2019, pp.1382-1396.
  12. C. Li, F. Wei, W. Dong, Q. Liu, Xiangfeng Wang, and X. Zhang, Dynamic Structure Embedded Online Multiple-output Regression for Streaming Data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 2019, pp.323-336.
  13. H. Yue, Q. Yang, Xiangfeng Wang, and X. Yuan, Implementing the ADMM to Big Datasets: A Case Study of LASSO. SIAM Journal on Scientific Computing, 40(5), 2018, pp.A3121-A3156.
  14. Xiangfeng Wang, W. Zhang, J. Yan, X. Yuan, and H. Zha, On the Flexibility of Block Coordinate Descent for Large-Scale Optimization. Neurocomputing, 272, 2018, pp.471-480.
  15. M. Hong, Xiangfeng Wang, M. Razaviyayn and Z.-Q. Luo, Iteration Complexity Analysis of Block Coordinate Descent Methods. Mathematical Programming Series A, 163, 2017, pp.85-114.
  16. T.-H. Chang, M. Hong, W.-C. Liao, and Xiangfeng Wang, Asynchronous Distributed ADMM for Large-Scale Optimization-Part I: Algorithm and Convergence Analysis. IEEE Transactions on Signal Processing, 64(12), 2016, pp.3118-3130.
  17. T.-H. Chang, W.-C. Liao, M. Hong, and Xiangfeng Wang, Asynchronous Distributed ADMM for Large-Scale Optimization-Part II: Linear Convergence Analysis and Numerical Performances. IEEE Transactions on Signal Processing, 64(12), 2016, pp.3131-3144.
  18. Xiangfeng Wang, On the Convergence Rate of a Class of Proximal-Based Decomposition Methods for Monotone Variational Inequalities. Journal of the Operations Research Society of China, 3(3), 2015, pp.347-362.
  19. Xiangfeng Wang, M. Hong, S. Ma, and Z.-Q. Luo, Solving Multiple-Block Separable Convex Minimization Problems using Two-Block ADMM. Pacific Journal of Optimization, 11(4), 2015, pp.645-667.
  20. T.-H. Chang, M. Hong, and Xiangfeng Wang, Multi-Agent Distributed Large-Scale Optimization by Inexact Consensus ADMM. IEEE Transactions on Signal Processing, 63(2), 2015, pp.482-497. ESI高被引论文 IEEE Signal Processing Society Best Paper Award
  21. X. Luo, Xiangfeng Wang, Z. Suo, and Z. Li, Efficient InSAR Phase Noise Reduction via Total Variation Regularization. Science China (Information Sciences), 2015, 58(8), 1-13.
  22. Xiangfeng Wang, and X. Yuan, The Linearized Alternating Direction Method of Multipliers for Dantzig Selector. SIAM Journal of Scientific Computing, 34(5), 2012, pp.A2792-A2811.

Conference

  1. J. Sheng, S. Cai, H. Cui, W. Li, Y. Hua, B. Jin, W. Zhou, Y. Hu, L. Zhu, Q. Peng, H. Zha and Xiangfeng Wang, VMAgent: A Practical Virtual Machine Scheduling Platform. IJCAI-Demos, 2022. (The VMAgent Simulator)
  2. W. Li, H. Chen, B. Jin, W. Tan, H. Zha, Xiangfeng Wang, Multi-Agent Path Finding with Prioritized Communication Learning. ICRA, 2022.
  3. T. Wu, W. Li, B. Jin, W. Zhang and Xiangfeng Wang, Weighted Mean-Field Multi-Agent Reinforcement Learning via Reward Attribution Decomposition. DASFAA, 2022.
  4. W. Li, Xiangfeng Wang, B. Jin, J. Sheng and H. Zha, Dealing with Non-Stationarity in Multi-Agent Reinforcement Learning via Trust Region Decomposition. ICLR, 2022.
  5. Y. Hua, Xiangfeng Wang, B. Jin, W. Li, J. Yan, X. He, and H. Zha, Hyper-Meta Reinforcement Learning with Sparse Reward. KDD, 2021.
  6. Q. Xu, Q. Wu, Y. Hu, B. Jin, B. Hu, F. Zhu, Y. Li, and Xiangfeng Wang, Semi-supervised Medical Image Segmentation with Confidence Calibration. IJCNN, 2021.
  7. W. Li, Xiangfeng Wang, B. Jin, J. Sheng, Y. Hua, and H. Zha, Structured Diversification Emergence via Reinforced Organization Control and Hierarchical Consensus Learning. AAMAS, 2021.
  8. X. Li, Xiangfeng Wang, B. Jin, W. Zhang, J. Wang, and H. Zha, VSB$^2$-Net: Visual-Semantic Bi-Branch Network for Zero-Shot Hashing. ICPR, 2020.
  9. J. Wang, Xiangfeng Wang, B. Jin, J. Yan, W. Zhang, and H. Zha, Heterogeneous Graph-based Knowledge Transfer for Generalized Zero-shot Learning. ICPR, 2020.
  10. X. Liao, W. Li, Q. Xu, Xiangfeng Wang, B. Jin, X. Zhang, Y. Zhang, and Y. Wang, Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning. CVPR, 2020.
  11. X. Li, X. Wen, B. Jin, Xiangfeng Wang, J. Wang, and J. Cai, Visual-to-Semantic Hashing for Zero-shot Learning. IJCNN, 2020.
  12. Y. Xie, Xiangfeng Wang, R. Wang, and H. Zha, A Fast Proximal Point Method for Computing Exact Wasserstein Distance. UAI, 2019.
  13. M. Zhang, C. Li, and Xiangfeng Wang, Multi-View Metric Learning for Multi-Label Image Classification. ICIP, 2019.
  14. W. Li, B. Jin, and Xiangfeng Wang, SparseMAAC: Sparse Attention for Multi-agent Reinforcement Learning. DASFAA, 2019.
  15. W. Zhang, J. Yan, Xiangfeng Wang, and H. Zha, Deep eXtreme Multi-label Learning. ICMR, 2018.
  16. X. Liu, J. Yan, S. Xiao, Xiangfeng Wang, H. Zha, and S. Chu, On Predictive Patent Valuation: Forecasting Patent Citations and Their Types. AAAI, 2017.
  17. T.-H. Chang, M. Hong, W.-C. Liao, and Xiangfeng Wang, Asynchronous Distributed Alternating Direction Method of Multipliers: Algorithm and Convergence Analysis. ICASSP, 2016.
  18. D. Hajinezhad, T.-H. Chang, Xiangfeng Wang, Q. Shi, and M. Hong, Nonnegative Matrix Factorization using ADMM: Algorithm and Convergence Analysis. ICASSP, 2016.
  19. S. Xiao, J. Yan, C. Li, B. Jin, Xiangfeng Wang, H. Zha, X. Yang, and S. Chu, On Modelling and Predicting Individual Paper Citation Count Over Time. IJCAI, 2016.
  20. J. Yan, S. Xiao, C. Li, B. Jin, Xiangfeng Wang, H. Zha, and X. Yang, Modelling Contagious M$\&$A via Point Processes with a Profile Regression Prior. IJCAI, 2016.
  21. C. Li, F. Wei, W. Dong, Xiangfeng Wang, J. Yan, X. Zhu, Q. Liu, and X. Zhang, Spatially Regularized Streaming Sensor Selection. AAAI, 2016.
  22. Xiangfeng Wang, M. Hong, T.-H. Chang, M. Razaviyayn, and Z.-Q. Luo, Joint Day-Ahead Power Procurement and Load Scheduling using Stochastic ADMM. ICASSP, 2014.
  23. H.-W. Tseng, S. Vishnubhotla, M. Hong, Xiangfeng Wang, J. Xiao, Z.-Q. Luo, and T. Zhang, A Single Channel Speech Enhancement Approach by Combining Statistical Criterion and Multi-Frame Sparse Dictionary Learning. INTERSPEECH, 2013.

Teaching

  • Multi-agent System (Multi-agent Reinforcement Learning)
  • Optimization for Machine Learning