User-Centric Federated Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

User-Centric Federated Learning

Résumé

Data heterogeneity across participating devices poses one of the main challenges in federated learning as it has been shown to greatly hamper its convergence time and generalization capabilities. In this work, we address this limitation by enabling personalization using multiple user-centric aggregation rules at the parameter server. Our approach potentially produces a personalized model for each user at the cost of some extra downlink communication overhead. To strike a trade-off between personalization and communication efficiency, we propose a broadcast protocol that limits the number of personalized streams while retaining the essential advantages of our learning scheme. Through simulation results, our approach is shown to enjoy higher personalization capabilities, faster convergence, and better communication efficiency compared to other competing baseline solutions.
Fichier principal
Vignette du fichier
publi-6686.pdf (594.89 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04143089 , version 1 (27-06-2023)

Identifiants

Citer

Mohamad Mestoukirdi, Matteo Zecchin, David Gesbert, Qianrui Li, Nicolas Gresset. User-Centric Federated Learning. GLOBECOM 2021, IEEE Globecom Workshops, IEEE, Dec 2021, Madrid, Spain. pp.1-6, ⟨10.1109/GCWkshps52748.2021.9682003⟩. ⟨hal-04143089⟩

Collections

EURECOM
15 Consultations
23 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More