FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning

In this paper, we identify a new phenomenon called activation-divergence which occurs in Federated Learning (FL) due to data heterogeneity (i.e., data being non-IID) across multiple users. Specifically, we argue that the activation vectors in FL can diverge, even if subsets of users share a few comm...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Chen, Wei, Bhardwaj, Kartikeya, Marculescu, Radu
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Statistics - Machine Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!