pith. sign in

arxiv: 2111.10192 · v1 · pith:RNAI22Q4new · submitted 2021-11-19 · 💻 cs.LG · stat.ML

An Expectation-Maximization Perspective on Federated Learning

classification 💻 cs.LG stat.ML
keywords learningfederatedmodelalgorithmhierarchicalcostsexpectation-maximizationfedavg
0
0 comments X
read the original abstract

Federated learning describes the distributed training of models across multiple clients while keeping the data private on-device. In this work, we view the server-orchestrated federated learning process as a hierarchical latent variable model where the server provides the parameters of a prior distribution over the client-specific model parameters. We show that with simple Gaussian priors and a hard version of the well known Expectation-Maximization (EM) algorithm, learning in such a model corresponds to FedAvg, the most popular algorithm for the federated learning setting. This perspective on FedAvg unifies several recent works in the field and opens up the possibility for extensions through different choices for the hierarchical model. Based on this view, we further propose a variant of the hierarchical model that employs prior distributions to promote sparsity. By similarly using the hard-EM algorithm for learning, we obtain FedSparse, a procedure that can learn sparse neural networks in the federated learning setting. FedSparse reduces communication costs from client to server and vice-versa, as well as the computational costs for inference with the sparsified network - both of which are of great practical importance in federated learning.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. FedGMI: Generative Model-Driven Federated Learning for Probabilistic Mixture Inference

    cs.LG 2026-05 unverdicted novelty 5.0

    FedGMI applies VAEs as density estimators in federated learning to infer mixture proportions of shared distributions for structured personalization under data heterogeneity.