Age-of-Information-Aware Federated Learning  

作　　者：徐殷 肖明军 吴晨 吴杰 周津锐 孙贺 Yin Xu;Ming-Jun Xiao;Chen Wu;Jie Wu;Jin-Rui Zhou;He Sun(Student Member,CCF 1.School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China;Suzhou Institute for Advanced Research,University of Science and Technology of China,Suzhou 215123,China;School of Data Science,University of Science and Technology of China,Hefei 230026,China;Department of Computer and Information Sciences,Temple University,Philadelphia,PA 19122,U.S.A.;CCF;IEEE)

机构地区：[1]Student Member,CCF 1.School of Computer Science and Technology,University of Science and Technology of China,Hefei 230026,China [2]Suzhou Institute for Advanced Research,University of Science and Technology of China,Suzhou 215123,China [3]School of Data Science,University of Science and Technology of China,Hefei 230026,China [4]Department of Computer and Information Sciences,Temple University,Philadelphia,PA 19122,U.S.A. [5]CCF [6]IEEE

出　　处：《Journal of Computer Science & Technology》2024年第3期637-653,共17页计算机科学技术学报（英文版）

基　　金：supported by the National Natural Science Foundation of China under Grant No.62172386;the Natural Science Foundation of Jiangsu Province of China under Grant No.BK20231212;the Teaching Research Project of the Education Department of Anhui Province of China under Grant No.2021jyxm1738.

摘　　要：Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central server.Unlike most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model training.Our primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained budget.To this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL system.Based on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)problem.Next,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple subproblems.Finally,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected clients.In addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关 键 词：federated learning Age of Information restless multi-armed bandit Whittle’s index 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]