Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

arXiv:2404.13804v1 Announce Type: cross
Abstract: Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling …

abstract algorithms analysis arxiv bandwidth client communication convergence cs.dc cs.lg cs.ni cs.sy eess.sy federated learning networks sample sampling server type unbiased wireless