Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

An oft-cited challenge of federated learning is the presence of heterogeneity. \emph{Data heterogeneity} refers to the fact that data from different clients may follow very different distributions. \emph{System heterogeneity} refers to client devices having different system capabilities. A considera...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-03
Hauptverfasser:	Nguyen, John, Wang, Jianyu, Malik, Kshitiz, Sanjabi, Maziar, Rabbat, Michael
Format:	Artikel
Sprache:	eng
Schlagworte:	Federated learning Heterogeneity Optimization
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!