Enhancing Federated Learning via Robust Client Behavior Eccentricity Analysis

Résumé fourni par la source

Federated Learning (FL) is a machine learning paradigm allowing collaborative model training across distributed nodes (clients) while preserving data privacy and security. However, effectively monitoring client behavior and evaluating contributions within FL environments remain significant challenges that need to be addressed. In this study, we demonstrate the scalability and robustness of the eccentricity analysis-based approach for monitoring client behavior in the FL setting through extensive experimentation, particularly in non-IID data scenarios. Our results show that clients’ eccentricity signatures can be used for analyzing clients’ behavioral patterns and understanding their contributions to the shared model.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.