Federated Learning for All: A Reinforcement Learning-Based Approach for Ensuring Fairness in Client Selection

In federated learning, selecting participating devices (clients) is critical due to their inherent diversity. Clients typically hold non-IID data and possess varying computational and communication capabilities, which introduces heterogeneity that can impact overall system performance. Ignoring this...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Saeedeh Ghazi, Saeed Farzi, Amirhossein Nikoofard
Format:	Artigo
Sprog:	Inglês
Udgivet:	IEEE 2025-01-01
Serier:	IEEE Access
Fag:	Client selection fairness federated learning reinforcement learning
Online adgang:	https://ieeexplore.ieee.org/document/11072670/
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!