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...

詳細記述

書誌詳細

出版年:	Scientific Reports
主要な著者:	Mai Shawkat, Zainab H. Ali, Mofreh Salem, Ali El-desoky
フォーマット:	論文
言語:	英語
出版事項:	Nature Portfolio 2025-04-01
主題:	Deep learning Federated learning Knowledge distillation Meta learning Privacy protection
オンライン･アクセス:	https://doi.org/10.1038/s41598-025-96468-8