人员队伍

首页» 人员队伍» 专任教师

沈力

 

　　教师简介

　　沈力，博士，中山大学网络空间安全学院副教授、博士生导师、逸仙学者。曾就职于京东探索研究院与腾讯人工智能实验室。此前分别于2013年和2017年在华南理工大学数学学院获得理学学士学位和运筹学与控制论博士学位。研究方向为大规模优化算法与理论及其在可信人工智能、统计机器学习、深度学习、强化学习中的应用。目前在机器学习与人工智能领域的旗舰期刊 （IEEE TPAMI、JMLR、IJCV等）和顶级会议（ICML、NeurIPS、ICLR、CVPR、ICCV等）发表论文100余篇，谷歌学术论文引用4000余次，专利授权20余项。担任人工智能顶级会议ICML、ICLR、ICPR、ACML 领域主席以及AAAI高级程序委员会成员。

　　 

　　研究兴趣

  • 可信人工智能：对抗攻防、鲁棒训练、差分隐私、大模型对齐
  • 强化学习：离线强化学习、多智能体、多任务强化学习、决策大模型
  • 协作学习：分布式机器学习、联邦学习、去中心化训练、多任务/持续学习、模型融合
  • 机器学习理论：稳定性与泛化误差界、PAC误差界、在线学习
  • 最优化算法与理论：随机优化、深度学习优化器、多目标优化、组合优化

　　 

　　团队招聘：团队长期与清华大学、新加坡国立大学、牛津大学、马里兰大学、悉尼大学、京东、阿里、腾讯等国内外知名科研机构合作。欢迎对以上方向感兴趣的同学（特聘研究员、特聘副研究员、博士后、博士研究生、硕士研究生、本科生、访问学生）加入课题组。

　　 

　　联系方式

　　邮箱：shenli6@mail.sysu.edu.cn、mathshenli@gmail.com

　　主页：https://sites.google.com/site/mathshenli/home

　　谷歌学术：https://scholar.google.com.hk/citations?user=yVhgENIAAAAJ&hl=en

　　DBLP：https://dblp.org/pid/91/3680-8.html

　　 

　　教育/工作经历

  1. 中山大学，网络空间安全学院，副教授/博士生导师
  2. 京东探索研究院，算法科学家
  3. 腾讯人工智能实验室，高级研究员
  4. 香港中文大学，系统工程与工程管理学院，访问学生
  5. 华南理工大学，数学学院，博士
  6. 华南理工大学，理学院，本科

　　 

　　论著

  • 代表性期刊
  1. Zhuo Huang, Muyang Li, Li Shen, Jun Yu, Chen Gong, Bo Han, Tongliang Liu, Winning Prize Comes from Losing Tickets: Improve Invariant Learning by Exploring Variant Parameters for Out-of-Distribution Generalization, International Journal of Computer Vision, 2024.
  2. Nan Yin, Li Shen, Huan Xiong, Bin Gu, Chong Chen, Xian-Sheng Hua, Siwei Liu, Xiao Luo, Messages Are Never Propagated Alone: Collaborative Hypergraph Neural Network for Time-series Forecasting, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  3. Zhenyi Wang, Li Shen, Tiehang Duan, Qiuling Suo, Le Fang, Wei Liu, Mingchen Gao, Distributionally Robust Memory Evolution with Generalized Divergence for Continual Learning,  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  4. Congliang Chen, Li Shen, Wei Liu, Zhi-Quan Luo, Efficient-Adam: Communication-Efficient Distributed Adam, IEEE Transactions on Signal Processing, 2023.
  5. Yan Sun, Li Shen, Hao Sun, Liang Ding, Dacheng Tao, Efficient Federated Learning via Local Adaptive Amended Optimizer with Linear Speedup, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  6. Zhihao Cheng, Li Shen, Miaoxi Zhu, Jiaxian Guo, Meng Fang, Liu Liu, Bo Du, Dacheng Tao, Prescribed Safety Performance Imitation Learning from A Single Expert Dataset, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023.
  7. Shiwei Liu, Yuesong Tian, Tianlong Chen, Li Shen, Don't Be So Dense: Sparse-to-Sparse GAN Training Without Sacrificing Performance, International Journal of Computer Vision, 2023.
  8. Hanchi Huang, Deheng Ye, Li Shen, Wei Liu, Curriculum-based Asymmetric Multi-task Reinforcement Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022.
  9. Congliang Chen, Li Shen, Fangyu Zou, Wei Liu, Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration, Journal of Machine Learning Research, 2022.
  10. Yuesong Tian, Li Shen, Li Shen, Guinan Su, Zhifeng Li, Wei Liu, AlphaGAN: Fully Differentiable Architecture Search for Generative Adversarial Networks, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  11. Xiaojun Chen, Weijun Hong, Feiping Nie, Joshua Zhexue Huang, Li Shen, Enhanced Balanced Min Cut, International Journal of Computer Vision, 2020.
  12. Baoyuan Wu, Li Shen, Tong Zhang, Bernard Ghanem, MAP Inference via L2-Sphere Linear Program Reformulation, International Journal of Computer Vision, 2020.

　　 

  • 代表性会议
  1. Yingqi Liu, Yifan Shi, Qinglun Li, Baoyuan Wu, Xueqian Wang, Li Shen, Directed Decentralized Collaboration for Personalized Federated Learning, CVPR, 2024.
  2. Zhiyuan Yu, Li Shen, Liang Ding, Xinmei Tian, Yixin Chen, Dacheng Tao, Sheared Backpropagation for Finetuning Foundation Models, CVPR, 2024.
  3. Ziming Hong, Li Shen, Tongliang Liu, Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning, CVPR, 2024.  
  4. Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao, A Free Lunch for Faster and Better Data-Free Meta-Learning, CVPR, 2024. 
  5. Yijun Yang, Tianyi Zhou, Kanxue Li, Dapeng Tao, Lusong Li, Li Shen, Xiaodong He, Jing Jiang, Yuhui Shi, Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld, CVPR, 2024.
  6. Jiayi Guan, Li Shen, Ao Zhou, Lusong Li, Han Hu, Xiaodong He, Guang Chen, Changjun Jiang, POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning, CVPR, 2024.
  7. Enneng Yang, Zhenyi Wang, Li Shen, Shiwei Liu, Guibing Guo, Xingwei Wang, Dacheng Tao, AdaMerging: Adaptive Model Merging for Multi-Task Learning, ICLR, 2024.
  8. Anke Tang, Li Shen, Yong Luo, Yibing Zhan, Han Hu, Bo Du, Yixin Chen, Dacheng Tao, Parameter-Efficient Multi-Task Model Fusion with Partial Linearization, ICLR, 2024.
  9. Shengchao Hu, Li Shen, Ya Zhang, Dacheng Tao, Learning Multi-Agent Communication from Graph Modeling Perspective, ICLR, 2024.
  10. Guozheng Ma, Lu Li, Sen Zhang, Zixuan Liu, Zhen Wang, Yixin Chen, Li Shen, Xueqian Wang, Dacheng Tao, Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages, ICLR, 2024.
  11. Zhenyi Wang, Yan Li, Li Shen, Heng Huang, A Unified and General Framework for Continual Learning, ICLR, 2024.
  12. Ziming Hong, Zhenyi Wang, Li Shen, Yu Yao, Zhuo Huang, Shiming Chen, Chuanwu Yang, Mingming Gong, Tongliang Liu, Improving Non-Transferable Representation Learning by Harnessing Content and Style, ICLR, 2024. (spotlight)
  13. Nan Yin, Mengzhu Wang, Zhenghan Chen, Li Shen, Huan Xiong, Bin Gu, Xiao Luo, DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption, ICLR, 2024.
  14. Yan Sun, Li Shen, Dacheng Tao, Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization, NeurIPS, 2023.
  15. Miaoxi Zhu, Li Shen, Bo Du, Dacheng Tao, Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm, NeurIPS, 2023.
  16. Zhenyi Wang, Li Shen, Tongliang Liu, Tiehang Duan, Yanjun Zhu, Donglin Zhan, David Doermann, Mingchen Gao, Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training, NeurIPS, 2023.
  17. Enneng Yang, Li Shen, Zhenyi Wang, Tongliang Liu, Guibing Guo, An Efficient Dataset Condensation Plugin and Its Application to Continual Learning, NeurIPS, 2023.
  18. Zhuo Huang, Li Shen, Jun Yu, Bo Han, Tongliang Liu, FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning, NeurIPS, 2023.
  19. Xuming An, Li Shen, Han Hu, Yong Luo, Federated Learning with Manifold Regularization and Normalized Update Reaggregation, NeurIPS, 2023. [paper]
  20. Rui Min, Zeyu Qin, Li Shen, Minhao Cheng, Stable Backdoor Purification with Feature Shift Tuning, NeurIPS, 2023.
  21. Guozheng Ma, Linrui Zhang, Haoyu Wang, Lu Li, Zilin Wang, Zhen Wang, Li Shen, Xueqian Wang, Dacheng Tao, Learning Better with Less: Effective Augmentation for Sample-Efficient Visual Reinforcement Learning, NeurIPS, 2023.
  22. Lu Yin, Gen Li, Meng Fang, Li Shen, Tianjin Huang, Zhangyang Wang, Vlado Menkovski, Xiaolong Ma, Mykola Pechenizkiy, Shiwei Liu, Dynamic Sparsity Is Channel-Level Sparsity Learner, NeurIPS, 2023.
  23. Yan Sun, Li Shen, Shixiang Chen, Liang Ding, Dacheng Tao, Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape, ICML, 2023. (oral)
  24. Zixuan Hu, Li Shen, Zhenyi Wang, Baoyuan Wu, Chun Yuan, Dacheng Tao, Learning to Learn from APIs: Black-box Data-free Meta-Learning, ICML, 2023.
  25. Yifan Shi, Li Shen, Kang Wei, Yan Sun, Bo Yuan, Xueqian Wang, Dacheng Tao, Improving the Model Consistency of Decentralized Federated Learning, ICML, 2023.
  26. Nan Yin, Li Shen, Mengzhu Wang, Long Lan, Zeyu Ma, Chong Chen, Xian-Sheng Hua, Xiao Luo, CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classification, ICML, 2023.
  27. Tianjin Huang, Lu Yin, Zhenyu Zhang, Li Shen, Meng Fang, Mykola Pechenizkiy, Zhangyang Wang, Shiwei Liu, Are Large Kernels Better Teachers than Transformers for ConvNets, ICML, 2023.
  28. Zixuan Hu, Li Shen, Zhenyi Wang, Tongliang Liu, Chun Yuan, Dacheng Tao, Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learning, CVPR, 2023.
  29. Zhenyi Wang, Li Shen, Donglin Zhan, Qiuling Suo, Yanjun Zhu, Tiehang Duan, Mingchen Gao, MetaMix: Towards Corruption-Robust Continual Learning with Temporally Self-Adaptive Data Transformation, CVPR, 2023.
  30. Yifan Shi, Yingqi Liu, Kang Wei, Li Shen, Xueqian Wang, Dacheng Tao, Make Landscape Flatter in Differentially Private Federated Learning, CVPR,  2023.
  31. Zhuo Huang, Miaoxi Zhu, Xiaobo Xia, Li Shen, Jun Yu, Chen Gong, Bo Han, Bo Du, Tongliang Liu, Robust Generalization against Corruptions via Worst-Case Sharpness Minimization, CVPR, 2023.
  32. Yan Sun, Li Shen, Tiansheng Huang, Liang Ding, Dacheng Tao, FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy, ICLR, 2023.
  33. Runzhong Wang, Li Shen, Yiting Chen, Xiaokang Yang, Dacheng Tao, Junchi Yan, Relaxed Combinatorial Optimization Networks with Self-Supervision: Theoretical and Empirical Notes on the Cardinality-Constrained Case, ICLR, 2023.
  34. Zhuo Huang, Xiaobo Xia, Li Shen, Bo Han, Mingming Gong, Chen Gong, Tongliang Liu, Harnessing Out-Of-Distribution Examples via Augmenting Content and Style, ICLR, 2023.
  35. Peng Mi, Li Shen, Tianhe Ren, Yiyi Zhou, Xiaoshuai Sun, Rongrong Ji, Dacheng Tao, Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach, NeurIPS, 2022.
  36. Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell, MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models, NeurIPS, 2022.
  37. Zeyu Qin, Yanbo Fan, Yi Liu, Li Shen, Yong Zhang, Jue Wang, Baoyuan Wu, Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation, NeurIPS, 2022.
  38. Zhenyi Wang, Li Shen, Le Fang, Qiuling Suo, Tiehang Duan, Mingchen Gao, Improving Task-free Continual Learning by Distributionally Robust Memory Evolution, ICML, 2022.
  39. Rong Dai, Li Shen, Fengxiang He, Xinmei Tian, Dacheng Tao, DisPFL: Towards Communication-Efficient Personalized Federated learning via Decentralized Sparse Training, ICML, 2022.
  40. Chang Liu, Chenfei Lou, Runzhong Wang, Alan Yuhan Xi, Li Shen, Junchi Yan, Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning, ICML, 2022.
  41. Chaojian Yu, Bo Han, Li Shen, Jun Yu, Chen Gong, Mingming Gong, Tongliang liu, Understanding Robust Overfitting of Adversarial Training and Beyond, ICML, 2022.
  42. Zhenyi Wang, Li Shen, Tiehang Duan, Donglin Zhan, Le Fang, Mingchen Gao, Learning to Learn and Remember Super Long Multi-Domain Task Sequence, CVPR, 2022. (oral)
  43. Lin Zhang, Li Shen, Liang Ding, Dacheng Tao, Lingyu Duan, Fine-tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning, CVPR, 2022.
  44. Shiwei Liu, Tianlong Chen, Xiaohan Chen, Li Shen, Decebal Constantin Mocanu, Zhangyang Wang, Mykola Pechenizkiy, The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training, ICLR, 2022.
  45. Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen, Dacheng Tao, Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning, ICLR, 2022.
  46. Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu, Sparse Training via Boosting Pruning Plasticity with Neuroregeneration, NeurIPS, 2021.
  47. Zhishuai Guo, Mingrui Liu, Zhuoning Yuan, Li Shen, Wei Liu, Tianbao Yang, Communication-Efficient Distributed Stochastic AUC Maximization with Deep Neural Networks, ICML, 2020.
  48. Fangyu Zou, Li Shen,  Zequn Jie, Weizhong Zhang, Wei Liu, A Sufficient Condition for Convergences of Adam and RMSProp, CVPR, 2019.(oral)
  49. Ganzhao Yuan, Li Shen, Wei-Shi Zheng, A Decomposition Algorithm for Sparse Generalized Eigenvalue Problem, CVPR, 2019.
  50. Li Shen, Peng Sun, Yitong Wang, Wei Liu, Tong Zhang, An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method, ICML, 2018.
  51. Li Shen, Wei Liu, Ganzhao Yuan, Shiqian Ma, GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization, ICML, 2017. 

　　 

  • 代表性专利
  1. 沈力；罗极羽；陶大程, 联邦学习的方法及分层网络系统、存储介质、电子设备, ZL202111042785.5
  2. 沈力；陶大程，差分隐私联邦学习训练方法、装置和计算机可读存储介质，ZL202310919570.X
  3. 沈力，训练模型和图像识别的方法和装置，ZL202110994071.8
  4. 沈力；董婧，模型训练方法、信息推送方法、装置、设备及存储介质，ZL202110938146.0
  5. 沈力；黄浩智；王璇，一种网络模型压缩方法、装置、存储介质和电子设备，ZL202010837744.4
  6. 沈力；张闯；宫辰，基于模型嵌入的鲁棒图像分类方法和装置，ZL20211 0898433.3
  7. 沈力；申丽；黄浩智；李志锋；刘威，图像识别模型的训练、图像识别方法、装置及设备，ZL202010657011.2
  8. 沈力；黄浩智；王璇；刘威，对象分类方法、训练方法、装置、设备及存储介质，ZL 202010662167.X
  9. 沈力；沈钰聪；黄浩智；王璇；刘威，机器学习模型压缩方法、装置、计算机设备和存储介质，ZL202010174061.5
  10. 沈力；陈淙靓；黄浩智；王璇；刘威，一种数据处理方法、装置及计算机可读存储介质，ZL202010520738.6

　　 

　　主要获奖

  1. 2022世界人工智能大会SAIL奖 (团队奖) 
  2. NeurIPS2020-SpicyFL workshop-best paper award

　　 

　　学术/社会兼职

  • 领域主席（AC）：ICML2024、ICLR2024、ICPR2024、ICPR2022
  • 高级程序委员（SPC）：AAAI2024、AAAI2022
  • 期刊审稿人：Journal of Machine Learning Research、IEEE Transactions on Pattern Analysis and Machine Intelligence、IEEE Transactions on Image Processing、IEEE Transactions on Neural Networks and Learning Systems、IEEE Transactions on Circuits and Systems for Video Technology、IEEE Transactions on Artificial Intelligence、IEEE Transactions on Cybernetics、IEEE Transactions on Network Science and Engineering、IEEE Transactions on Automation Science and Engineering、Machine Learning、Pattern Recognition等
  • 会议审稿人：NeurIPS、ICML、ICLR、CVPR、ICCV、ECCV、ACL、AAAI等