FedPop: A Bayesian Approach for Personalised Federated Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

FedPop: A Bayesian Approach for Personalised Federated Learning

Maxime Vono
Eric Moulines
Alain Durmus

Résumé

Personalised federated learning (FL) aims at collaboratively learning a machine learning model taylored for each client. Albeit promising advances have been made in this direction, most of existing approaches works do not allow for uncertainty quantification which is crucial in many applications. In addition, personalisation in the cross-device setting still involves important issues, especially for new clients or those having small number of observations. This paper aims at filling these gaps. To this end, we propose a novel methodology coined FedPop by recasting personalised FL into the population modeling paradigm where clients' models involve fixed common population parameters and random effects, aiming at explaining data heterogeneity. To derive convergence guarantees for our scheme, we introduce a new class of federated stochastic optimisation algorithms which relies on Markov chain Monte Carlo methods. Compared to existing personalised FL methods, the proposed methodology has important benefits: it is robust to client drift, practical for inference on new clients, and above all, enables uncertainty quantification under mild computational and memory overheads. We provide non-asymptotic convergence guarantees for the proposed algorithms and illustrate their performances on various personalised federated learning tasks.
Fichier principal
Vignette du fichier
2206.03611.pdf (1.19 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03959047 , version 1 (26-01-2023)

Identifiants

  • HAL Id : hal-03959047 , version 1

Citer

Nikita Kotelevskii, Maxime Vono, Eric Moulines, Alain Durmus. FedPop: A Bayesian Approach for Personalised Federated Learning. NeurIPS 2022, Nov 2022, New Orleans (US), United States. ⟨hal-03959047⟩

Collections

X IP_PARIS
27 Consultations
21 Téléchargements

Partager

Gmail Facebook X LinkedIn More