Fed-ZOE: Communication-Efficient Over-the-Air Federated Learning via Zeroth-Order Estimation

As 6G and beyond networks grow increasingly complex and interconnected, federated learning (FL) emerges as an indispensable paradigm for securely and efficiently leveraging decentralized edge data for AI. By virtue of the superposition property of communication signals, over-the-air FL (OtA-FL) achi...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-12
Hauptverfasser:	Jang, Jonggyu, Lyu, Hyeonsu, Love, David J, Hyun Jong Yang
Format:	Artikel
Sprache:	eng
Schlagworte:	Communication Federated learning Machine learning Neural networks Parameters Superposition (mathematics) Symbols
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!