FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning

TL;DR

FedPAE is a decentralized federated learning method that enables asynchronous, model-heterogeneous collaboration among clients, improving scalability and robustness over existing approaches.

Contribution

Introduces FedPAE, a peer-to-peer ensemble learning algorithm for asynchronous, model-heterogeneous federated learning without centralized coordination.

Findings

Outperforms state-of-the-art pFL algorithms in diverse settings.

Effectively manages client heterogeneity and statistical variability.

Supports fully decentralized and asynchronous training.

Abstract

Federated learning (FL) enables multiple clients with distributed data sources to collaboratively train a shared model without compromising data privacy. However, existing FL paradigms face challenges due to heterogeneity in client data distributions and system capabilities. Personalized federated learning (pFL) has been proposed to mitigate these problems, but often requires a shared model architecture and a central entity for parameter aggregation, resulting in scalability and communication issues. More recently, model-heterogeneous FL has gained attention due to its ability to support diverse client models, but existing methods are limited by their dependence on a centralized framework, synchronized training, and publicly available datasets. To address these limitations, we introduce Federated Peer-Adaptive Ensemble Learning (FedPAE), a fully decentralized pFL algorithm that supports model heterogeneity and asynchronous learning. Our approach utilizes a peer-to-peer model sharing mechanism and ensemble selection to achieve a more refined balance between local and global information. Experimental results show that FedPAE outperforms existing state-of-the-art pFL algorithms, effectively managing diverse client capabilities and demonstrating robustness against statistical heterogeneity.