DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning

doi:10.1109/TCOMM.2023.3288591

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 听觉模型与认知计算

	DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning
	Lin, Yijing 1; Gao, Zhipeng 1; Du, Hongyang 2; Kang, Jiawen 3; Niyato, Dusit 2; Wang, Qian 4; Ruan, Jingqing 5; Wan, Shaohua 6
刊名	IEEE TRANSACTIONS ON COMMUNICATIONS
	2023-10-01
卷号	71 期号:10 页码:5992-6004
关键词	Blockchain sharding federated learning reputation deep reinforcement learning
ISSN号	0090-6778
DOI	10.1109/TCOMM.2023.3288591
通讯作者	Gao, Zhipeng(gaozhipeng@bupt.edu.cn)
英文摘要	Blockchain-based Federated Learning (FL) technology enables vehicles to make smart decisions, improving vehicular services and enhancing the driving experience through a secure and privacy-preserving manner in Intelligent Transportation Systems (ITS). Many existing works exploit two-layer blockchain-based FL frameworks consisting of a mainchain and subchains for data interactions among intelligent vehicles, which resolve the limited throughput issue of single blockchain-based vehicular networks. However, the existing two-layer frameworks still suffer from a) strong dependency on predetermined and fixed parameters of vehicular blockchains which limit blockchain throughput and reliability; and b) high communication costs incurred by interactions among intelligent vehicles between the mainchain and subchains. To address the above challenges, we first design an adaptive blockchain-enabled FL framework for ITS based on blockchain sharding to facilitate decentralized vehicular data flows among intelligent vehicles. A streamline-based shard transmission mechanism is proposed to ensure communication efficiency almost without compromising the FL accuracy. We further formulate the proposed framework and propose an adaptive sharding mechanism using Deep Reinforcement Learning to automate the selection of parameters of vehicular shards. Numerical results clearly show that the proposed framework and mechanisms achieve adaptive, communication-efficient, credible, and scalable data interactions among intelligent vehicles.
资助项目	National Natural Science Foundation of China[62072049] ; National Natural Science Foundation of China[62101012] ; National Natural Science Foundation of China[62102099] ; BUPT Innovation and Entrepreneurship Support Program[2023-YC-A131] ; National Research Foundation, Singapore ; Infocomm Media Development Authority under its Future Communications Research & Development Programme ; DSO National Laboratories under the AI Singapore Programme[AISG2-RP-2020-019] ; Energy Research Test-Bed and Industry Partnership Funding Initiative ; Energy Grid (EG) 2.0 programme ; Campus for Research Excellence and Technological Enterprise (CREATE) programme ; MOE Tier 1[RG87/22]
WOS关键词	INTERNET ; OPTIMIZATION
WOS研究方向	Engineering ; Telecommunications
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001164689800002
资助机构	National Natural Science Foundation of China ; BUPT Innovation and Entrepreneurship Support Program ; National Research Foundation, Singapore ; Infocomm Media Development Authority under its Future Communications Research & Development Programme ; DSO National Laboratories under the AI Singapore Programme ; Energy Research Test-Bed and Industry Partnership Funding Initiative ; Energy Grid (EG) 2.0 programme ; Campus for Research Excellence and Technological Enterprise (CREATE) programme ; MOE Tier 1
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/57838]
专题	数字内容技术与服务研究中心_听觉模型与认知计算
通讯作者	Gao, Zhipeng
作者单位	1.Beijing Univ Posts & Telecommun, State Key Lab Networking & Switching Technol, Beijing 100876, Peoples R China 2.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639798, Singapore 3.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Peoples R China 4.Beijing Univ Technol, Coll Comp Sci, Beijing 100124, Peoples R China 5.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 6.Univ Elect Sci & Technol China, Shenzhen Inst Adv Study, Shenzhen 518110, Peoples R China
推荐引用方式 GB/T 7714	Lin, Yijing,Gao, Zhipeng,Du, Hongyang,et al. DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning[J]. IEEE TRANSACTIONS ON COMMUNICATIONS,2023,71(10):5992-6004.
APA	Lin, Yijing.,Gao, Zhipeng.,Du, Hongyang.,Kang, Jiawen.,Niyato, Dusit.,...&Wan, Shaohua.(2023).DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning.IEEE TRANSACTIONS ON COMMUNICATIONS,71(10),5992-6004.
MLA	Lin, Yijing,et al."DRL-Based Adaptive Sharding for Blockchain-Based Federated Learning".IEEE TRANSACTIONS ON COMMUNICATIONS 71.10(2023):5992-6004.