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...

Descripció completa

Dades bibliogràfiques

Autors principals:	Mai Shawkat, Zainab H. Ali, Mofreh Salem, Ali El-desoky
Format:	Artigo
Idioma:	Inglês
Publicat:	Nature Portfolio 2025-04-01
Col·lecció:	Scientific Reports
Matèries:	Deep learning Federated learning Knowledge distillation Meta learning Privacy protection
Accés en línia:	https://doi.org/10.1038/s41598-025-96468-8
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!