Customized Federated Learning for accelerated edge computing with heterogeneous task targets

doi:10.1016/j.comnet.2020.107569

	Customized Federated Learning for accelerated edge computing with heterogeneous task targets
	Jiang, Hui 1; Liu, Min 1; Yang, Bo 1; Liu, Qingxiang 1; Li, Jizhong 2; Guo, Xiaobing 3
	2020-12-24
发表期刊	COMPUTER NETWORKS
ISSN	1389-1286
卷号	183 页码:13
摘要	As a dominant edge intelligence technique, Federated Learning (FL) can reduce the data transmission volume, shorten the communication latency and improve the collaboration efficiency among end-devices and edge servers. Existing works on FL-based edge computing only take device- and resource-heterogeneity into consideration under a fixed loss-minimization objective. As heterogeneous end-devices are usually assigned with various tasks with different target accuracies, task heterogeneity is also a significant issue and has not yet been investigated. To this end, we propose a Customized FL (CuFL) algorithm with an adaptive learning rate to tailor for heterogeneous accuracy requirements and to accelerate the local training process. We also present a fair global aggregation strategy for the edge server to minimize the variance of accuracy gaps among heterogeneous end-devices. We rigorously analyze the convergence property of the CuFL algorithm in theory. We also verify the feasibility and effectiveness of the CuFL algorithm in the vehicle classification task. Evaluation results demonstrate that our algorithm performs better in terms of the accuracy rate, training time, and fairness during aggregation than existing efforts.
关键词	Edge computing Federated Learning Convergence performance
DOI	10.1016/j.comnet.2020.107569
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61732017] ; National Natural Science Foundation of China[62072436] ; National Natural Science Foundation of China[61872028]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:000599651100014
出版者	ELSEVIER
引用统计	被引频次：17[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/16530
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Min
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing, Peoples R China 2.Huawei Technol Co Ltd, Cent Software Inst, Beijing, Peoples R China 3.Lenovo Res, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Jiang, Hui,Liu, Min,Yang, Bo,et al. Customized Federated Learning for accelerated edge computing with heterogeneous task targets[J]. COMPUTER NETWORKS,2020,183:13.
APA	Jiang, Hui,Liu, Min,Yang, Bo,Liu, Qingxiang,Li, Jizhong,&Guo, Xiaobing.(2020).Customized Federated Learning for accelerated edge computing with heterogeneous task targets.COMPUTER NETWORKS,183,13.
MLA	Jiang, Hui,et al."Customized Federated Learning for accelerated edge computing with heterogeneous task targets".COMPUTER NETWORKS 183(2020):13.