Convergence Analysis and Latency Minimization for Retransmission-Based Semi-Federated Learning

In this paper, we propose a semi-federated learning (SemiFL) framework to ameliorate the performance of conventional federated learning. The base station and devices are coordinated to collaboratively train a shared model. However, due to the rapidly fluctuating channels and irrationally assigned lo...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE Global Communications Conference (Online) S. 2057 - 2062
Hauptverfasser:	Zheng, Jingheng, Ni, Wanli, Tian, Hui, Jiang, Wenchao, Quek, Tony Q. S.
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 04.12.2023
Schlagworte:	Central Processing Unit Closed-form solutions Computational modeling Convergence convergence analysis Data models latency minimization Minimization over-the-air computation retransmission Semi-federated learning Simulation
ISSN:	2576-6813
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!