Knowledge Commons of Institute of Automation,CAS
R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications | |
Zhang, Weishan1,2; Yu, Fa1,3; Wang, Xiao4,5; Zeng, Xingjie1; Zhao, Hongwei1; Tian, Yonglin6; Wang, Fei-Yue6; Li, Longfei7; Li, Zengxiang3 | |
发表期刊 | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS |
ISSN | 1551-3203 |
2023-08-01 | |
卷号 | 19期号:8页码:8829-8840 |
通讯作者 | Zhang, Weishan(zhangws@upc.edu.cn) |
摘要 | Federated learning has become an emerging hot research field in industry because of its ability to perform large-scale distributed learning while preserving data privacy. However, recent studies have shown that in the actual use of federated learning, there are device heterogeneity and data not identically and independently distributed (Non-IID) characteristics between client nodes, which will affect the effect of federated learning. In this work, we propose resilient reinforcement federated learning (R(2)Fed), a R(2)Fed method, which applies reinforcement learning to federated learning and uses reinforcement learning for weighted fusion of client models instead of average fusion. We conduct experiments on object detection, object classification, and sentiment classification tasks in the context of Non-IID and heterogeneity, and the experimental results show that the R(2)Fed method outperforms traditional federated learning, increasing the average accuracy by 4.7%. Experiments also demonstrate that R(2)Fed is resilient to federation attacks. |
关键词 | Federated learning non-independent identically distributed (non-IID) data reinforcement learning |
DOI | 10.1109/TII.2022.3222369 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[62072469] ; Opening Project of the State Key Laboratory for Management and Control Complex Systems, Institute of Automation, Chinese Academy of Sciences[20210114] |
项目资助者 | National Natural Science Foundation of China ; Opening Project of the State Key Laboratory for Management and Control Complex Systems, Institute of Automation, Chinese Academy of Sciences |
WOS研究方向 | Automation & Control Systems ; Computer Science ; Engineering |
WOS类目 | Automation & Control Systems ; Computer Science, Interdisciplinary Applications ; Engineering, Industrial |
WOS记录号 | WOS:001030673600026 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/53901 |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Zhang, Weishan |
作者单位 | 1.China Univ Petr East China, Coll Comp Sci & Technol, Qingdao 266580, Peoples R China 2.Qingdao Acad Intelligent Ind QAII, Qingdao 230031, Peoples R China 3.ENN Grp, Inst Digital Res, Langfang 065000, Peoples R China 4.Anhui Univ, Sch Artificial Intelligence, Hefei 266114, Anhui, Peoples R China 5.Qingdao Acad Intelligent Ind QAII, Qingdao 230031, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing 100086, Peoples R China 7.Space Star Technol Co Ltd, Beijing 100095, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Weishan,Yu, Fa,Wang, Xiao,et al. R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2023,19(8):8829-8840. |
APA | Zhang, Weishan.,Yu, Fa.,Wang, Xiao.,Zeng, Xingjie.,Zhao, Hongwei.,...&Li, Zengxiang.(2023).R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,19(8),8829-8840. |
MLA | Zhang, Weishan,et al."R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 19.8(2023):8829-8840. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论