Semi-decentralized federated learning with client pairing for efficient mutual knowledge transfer

Abstract In Decentralized Federated Learning (DFL), Deep Mutual Learning (DML) improves global accuracy under non-independent and identically distributed (non-IID) data by enabling knowledge exchange over clients, but introduces extra training overhead and delays convergence. To solve this issue, we...

Descrición completa

Detalles Bibliográficos

Principais autores:	Dain Yang, Joohyung Lee, Seong Gon Choi
Formato:	Artigo
Idioma:	Inglês
Publicado:	Nature Portfolio 2025-11-01
Series:	Scientific Reports
Assuntos:	Data heterogeneity Decentralized federated learning Knowledge transfer
Acceso en liña:	https://doi.org/10.1038/s41598-025-29491-4
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!