Contribution‐based Federated Learning client selection

Federated Learning (FL), as a privacy‐preserving machine learning paradigm, has been thrusted into the limelight. As a result of the physical bandwidth constraint, only a small number of clients are selected for each round of FL training. However, existing client selection solutions (e.g., the vanil...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	International journal of intelligent systems 2022-10, Vol.37 (10), p.7235-7260
Hauptverfasser:	Lin, Weiwei, Xu, Yinhai, Liu, Bo, Li, Dongdong, Huang, Tiansheng, Shi, Fang
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms client Clients contribution‐based, EXP3 Convergence Decision theory Federated Learning global models Intelligent systems Machine learning Model accuracy Non‐Independent Identically Distributed Scaling factors
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!