Federated learning with joint server-client momentum

具有联合服务器-客户端动量的联邦学习

阅读:1

Abstract

Federated Learning, an approach to collaborative modeling, enables the training of a unified global model across multiple clients in a decentralized manner. However, the considerable impact of local data heterogeneity on algorithm performance has attracted significant attention. In this study, we introduce a novel Federated Learning algorithm called Federated Joint Server-Client Momentum (FedJSCM) to address data heterogeneity in real-world Federated Learning applications. FedJSCM efficiently utilizes global gradient information from previous communications and adjusts client gradient descent and server model fusion by transmitting gradient momentum information. This corrective mechanism effectively mitigates biases and improves the stability of Stochastic Gradient Descent (SGD). We offer theoretical analysis to highlight the advantages of FedJSCM and conduct extensive empirical studies, showcasing its superior performance across various tasks and its robustness in the face of varying degrees of data heterogeneity. Empirical studies demonstrate that FedJSCM outperforms existing algorithms, with a 1-3% accuracy increase.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。