An Expectation-Maximization Perspective on Federated Learning

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.

References in corpus (20)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
• Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
• On First-Order Meta-Learning Algorithms
• The State of Sparsity in Deep Neural Networks
• Federated Optimization in Heterogeneous Networks
• Improving Federated Learning Personalization via Model Agnostic Meta Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Recasting Gradient-Based Meta-Learning as Hierarchical Bayes
• Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
• Bayesian Nonparametric Federated Learning of Neural Networks
• Adaptive Federated Optimization
• Variational Federated Multi-Task Learning
• Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms
• Federated Learning With Quantized Global Model Updates
• Double Quantization for Communication-Efficient Distributed Optimization
• Learned Threshold Pruning
• PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization
• Modular Meta-Learning with Shrinkage