Communication-Efficient Federated Learning with Accelerated Client Gradient

arXiv:2201.03172v2 Announce Type: replace
Abstract: Federated learning often suffers from slow and unstable convergence due to the heterogeneous characteristics of participating client datasets. Such a tendency is aggravated when the client participation ratio is low since the information collected from the clients has large variations. To address this challenge, we propose a simple but effective federated learning framework, which improves the consistency across clients and facilitates the convergence of the server model. This is achieved by making the server broadcast …

abstract arxiv challenge client communication convergence cs.ai cs.lg datasets federated learning gradient information low simple the information type