R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications

doi:10.1109/TII.2022.3222369

	R(2)Fed: Resilient Reinforcement Federated Learning for Industrial Applications
	Zhang, Weishan 1,2; Yu, Fa 1,3; Wang, Xiao4,5 ; Zeng, Xingjie 1; Zhao, Hongwei 1; Tian, Yonglin6 ; Wang, Fei-Yue6 ; Li, Longfei 7; Li, Zengxiang 3
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	被引频次：8[WOS] [WOS记录] [WOS相关记录]
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.