Federated learning has emerged as a distributed learning paradigm by training at each client and aggregat-ing at a parameter server.System heterogeneity hinders stragglers from responding to the server in time with hu...Federated learning has emerged as a distributed learning paradigm by training at each client and aggregat-ing at a parameter server.System heterogeneity hinders stragglers from responding to the server in time with huge com-munication costs.Although client grouping in federated learning can solve the straggler problem,the stochastic selection strategy in client grouping neglects the impact of data distribution within each group.Besides,current client grouping ap-proaches make clients suffer unfair participation,leading to biased performances for different clients.In order to guaran-tee the fairness of client participation and mitigate biased local performances,we propose a federated dynamic client selec-tion method based on data representativity(FedSDR).FedSDR clusters clients into groups correlated with their own lo-cal computational efficiency.To estimate the significance of client datasets,we design a novel data representativity evalua-tion scheme based on local data distribution.Furthermore,the two most representative clients in each group are selected to optimize the global model.Finally,the DYNAMIC-SELECT algorithm updates local computational efficiency and data representativity states to regroup clients after periodic average aggregation.Evaluations on real datasets show that FedS-DR improves client participation by 27.4%,37.9%,and 23.3%compared with FedAvg,TiFL,and FedSS,respectively,tak-ing fairness into account in federated learning.In addition,FedSDR surpasses FedAvg,FedGS,and FedMS by 21.32%,20.4%,and 6.90%,respectively,in local test accuracy variance,balancing the performance bias of the global model across clients.展开更多
基金This work is supported by the National Key Research and Development Program of China under Grant No.2022YFC3005401the Key Research and Development Program of Yunnan Province of China under Grant No.202203AA080009+1 种基金the Transformation Program of Scientific and Technological Achievements of Jiangsu Province of China under Grant No.BA2021002the Key Research and Development Program of Jiangsu Province of Chin under Grant No.BE2020729.
文摘Federated learning has emerged as a distributed learning paradigm by training at each client and aggregat-ing at a parameter server.System heterogeneity hinders stragglers from responding to the server in time with huge com-munication costs.Although client grouping in federated learning can solve the straggler problem,the stochastic selection strategy in client grouping neglects the impact of data distribution within each group.Besides,current client grouping ap-proaches make clients suffer unfair participation,leading to biased performances for different clients.In order to guaran-tee the fairness of client participation and mitigate biased local performances,we propose a federated dynamic client selec-tion method based on data representativity(FedSDR).FedSDR clusters clients into groups correlated with their own lo-cal computational efficiency.To estimate the significance of client datasets,we design a novel data representativity evalua-tion scheme based on local data distribution.Furthermore,the two most representative clients in each group are selected to optimize the global model.Finally,the DYNAMIC-SELECT algorithm updates local computational efficiency and data representativity states to regroup clients after periodic average aggregation.Evaluations on real datasets show that FedS-DR improves client participation by 27.4%,37.9%,and 23.3%compared with FedAvg,TiFL,and FedSS,respectively,tak-ing fairness into account in federated learning.In addition,FedSDR surpasses FedAvg,FedGS,and FedMS by 21.32%,20.4%,and 6.90%,respectively,in local test accuracy variance,balancing the performance bias of the global model across clients.
