LGAICVMar 30, 2021

Model-Contrastive Federated Learning

arXiv:2103.16257v11669 citations
Originality Highly original
AI Analysis

This addresses data heterogeneity issues in federated learning for image datasets, offering a novel solution that outperforms existing methods.

The paper tackles the challenge of data heterogeneity in federated learning by proposing MOON, a model-contrastive framework that corrects local training using model representation similarity, achieving significant performance improvements on image classification tasks.

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.

Code Implementations6 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes