Federated Mutual Learning

TL;DR

Federated Mutual Learning (FML) introduces a new FL paradigm enabling clients to collaboratively learn a generalized model while maintaining personalized and customized models, effectively addressing data heterogeneity and task diversity.

Contribution

FML is a novel federated learning framework that handles data heterogeneity, personalized models, and customized client models simultaneously, improving performance over existing methods.

Findings

FML outperforms alternative methods in typical FL settings.

Clients benefit from FML with different models and tasks.

FML effectively leverages data heterogeneity as an advantage.

Abstract

Federated learning (FL) enables collaboratively training deep learning models on decentralized data. However, there are three types of heterogeneities in FL setting bringing about distinctive challenges to the canonical federated learning algorithm (FedAvg). First, due to the Non-IIDness of data, the global shared model may perform worse than local models that solely trained on their private data; Second, the objective of center server and clients may be different, where center server seeks for a generalized model whereas client pursue a personalized model, and clients may run different tasks; Third, clients may need to design their customized model for various scenes and tasks; In this work, we present a novel federated learning paradigm, named Federated Mutual Leaning (FML), dealing with the three heterogeneities. FML allows clients training a generalized model collaboratively and a personalized model independently, and designing their private customized models. Thus, the Non-IIDness of data is no longer a bug but a feature that clients can be personally served better. The experiments show that FML can achieve better performance than alternatives in typical FL setting, and clients can be benefited from FML with different models and tasks.