Global prototype distillation for heterogeneous federated learning

Abstract Federated learning is a distributed machine learning paradigm where the goal is to collaboratively train a high quality global model while private training data remains local over distributed clients. However, heterogenous data distribution over clients is severely challenging for federated...

Cijeli opis

Bibliografski detalji

Glavni autori:	Shu Wu, Jindou Chen, Xueli Nie, Yong Wang, Xiancun Zhou, Linlin Lu, Wei Peng, Yao Nie, Waseef Menhaj
Format:	Artigo
Jezik:	Inglês
Izdano:	Nature Portfolio 2024-05-01
Serija:	Scientific Reports
Teme:	Federated learning Knowledge distillation Data heterogeneity
Online pristup:	https://doi.org/10.1038/s41598-024-62908-0
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!