Timezone: »

 
Poster
FedPop: A Bayesian Approach for Personalised Federated Learning
Nikita Kotelevskii · Maxime Vono · Alain Durmus · Eric Moulines

Tue Nov 29 09:00 AM -- 11:00 AM (PST) @ Hall J #143
in Poster Session 1 »

Personalised federated learning (FL) aims at collaboratively learning a machine learning model tailored for each client. Albeit promising advances have been made in this direction, most of the existing approaches do not allow for uncertainty quantification which is crucial in many applications. In addition, personalisation in the cross-silo and cross-device setting still involves important issues, especially for new clients or those having a 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 that 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 nonasymptotic convergence guarantees for the proposed algorithms and illustrate their performances on various personalised federated learning tasks.

Keywords: MCMC · federated learning · bayesian inference · latent variable
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Nikita Kotelevskii (Skolkovo Institute of Science and Technology)
Maxime Vono (Criteo AI Lab)
Alain Durmus (Ecole polytechnique)
Eric Moulines (Ecole Polytechnique)

More from the Same Authors