SACW: Semi-Asynchronous Federated Learning with Client Selection and Adaptive Weighting

Federated learning (FL), as a privacy-preserving distributed machine learning paradigm, demonstrates unique advantages in addressing data silo problems. However, the prevalent statistical heterogeneity (data distribution disparities) and system heterogeneity (device capability variations) in practic...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Computers (Basel) Jg. 14; H. 11; S. 464
Hauptverfasser:	Li, Shuaifeng, Shan, Fangfang, Mao, Shiqi, Lu, Yanlong, Miao, Fengjun, Chen, Zhuo
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Basel MDPI AG 01.11.2025
Schlagworte:	Adaptive algorithms adaptive weighting Algorithms Artificial intelligence client clustering client selection Clustering Communication Distributed processing (Computers) Efficiency Electronic data processing Federated learning File servers Heterogeneity Homogeneity Information management Internet of Things Machine learning Methods Resource utilization semi-asynchronous federated learning Servers statistical heterogeneity Synchronism system heterogeneity Weighting Florida New York China
ISSN:	2073-431X, 2073-431X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!