Stabilizing and Accelerating Federated Learning on Heterogeneous Data With Partial Client Participation
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Pattern Analysis and Machine Intelligence"
DOI: 10.1109/tpami.2024.3469188
Abstract: Federated learning (FL) commonly encourages the clients to perform multiple local updates before the global aggregation, thus avoiding frequent model exchanges and relieving the communication bottleneck between the server and clients. Though empirically effective, the… read more here.
Keywords: multiple local; local update; stability; local updates ... See more keywords