FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks

arXiv:2404.14811v1 Announce Type: cross
Abstract: Wireless federated learning (WFL) suffers from heterogeneity prevailing in the data distributions, computing powers, and channel conditions of participating devices. This paper presents a new Federated Learning with Adjusted leaRning ratE (FLARE) framework to mitigate the impact of the heterogeneity. The key idea is to allow the participating devices to adjust their individual learning rates and local training iterations, adapting to their instantaneous computing powers. The convergence upper bound of FLARE is established rigorously under …

abstract arxiv computing cs.lg data devices eess.sp federated learning framework impact networks paper rate type wireless