A robust and personalized privacy-preserving approach for adaptive clustered federated distillation

Abstract Federated learning (FL) is a promising approach that addresses privacy, and scalability concerns in contrast to traditional centralized methods. Challenges such as personalization and data heterogeneity issues remain critical. Clustered federated learning (CFL) has been proposed as a promis...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Mai Shawkat, Zainab H. Ali, Mofreh Salem, Ali El-desoky
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Nature Portfolio 2025-04-01
Edice:	Scientific Reports
Témata:	Deep learning Federated learning Knowledge distillation Meta learning Privacy protection
On-line přístup:	https://doi.org/10.1038/s41598-025-96468-8
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!