Personalized lightweight federated learning for efficient and private model training in heterogeneous data environments

Personalized federated learning (PFL) enables collaborative model training across devices while adapting to heterogeneous data, but faces resource constraints on edge devices. Combining PFL with pruning techniques helps address these constraints. A challenge is that one-size-fits-all pruning strateg...

Celý popis

Podrobná bibliografie

Hlavní autor:	Ying Wang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Elsevier 2025-12-01
Edice:	Systems and Soft Computing
Témata:	Personalized lightweight federated learning Pruning Hy-pernetwork Model training Heterogeneous data
On-line přístup:	http://www.sciencedirect.com/science/article/pii/S2772941925000304
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!