Model-Contrastive Federated Learning

Abstract

Federated learning enables multiple parties to collaboratively train a machine learning model without communicating their local data. A key challenge in federated learning is to handle the heterogeneity of local data distribution across parties. Although many studies have been proposed to address this challenge, we find that they fail to achieve high performance in image datasets with deep learning models. In this paper, we propose MOON: model-contrastive federated learning. MOON is a simple and effective federated learning framework. The key idea of MOON is to utilize the similarity between model representations to correct the local training of individual parties, i.e., conducting contrastive learning in model-level. Our extensive experiments show that MOON significantly outperforms the other state-of-the-art federated learning algorithms on various image classification tasks.

Accepted by CVPR 2021

References in corpus (5)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Bootstrap your own latent: A new approach to self-supervised Learning
• Bayesian Nonparametric Federated Learning of Neural Networks
• Federated Learning with Matched Averaging
• Lower Bounds and Optimal Algorithms for Personalized Federated Learning