FedGiA: An Efficient Hybrid Algorithm for Federated Learning

Shenglong Zhou, Geoffrey Ye Li

Publication date: 3 May 2022

Abstract: Federated learning has shown its advances recently but is still facing many challenges, such as how algorithms save communication resources and reduce computational costs, and whether they converge. To address these critical issues, we propose a hybrid federated learning algorithm (FedGiA) that combines the gradient descent and the inexact alternating direction method of multipliers. The proposed algorithm is more communication- and computation-efficient than several state-of-the-art algorithms theoretically and numerically. Moreover, it also converges globally under mild conditions.

Has companion code repository: https://github.com/shenglongzhou/fedgia

This page was built for publication: FedGiA: An Efficient Hybrid Algorithm for Federated Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6398124)