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

Brianna Mueller; W. Nick Street; Stephen Baek; Qihang Lin; Jingyi Yang; Yankun Huang

doi:10.48550/arxiv.2410.14075

Back

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

Preprint

Open access

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

Brianna Mueller, W. Nick Street, Stephen Baek, Qihang Lin, Jingyi Yang and Yankun Huang

ArXiv.org

Cornell University

10/17/2024

DOI: 10.48550/arxiv.2410.14075

Files and links (1)

url

https://doi.org/10.48550/arxiv.2410.14075View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

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.

Computer Science - Learning

Details

Title: Subtitle: FedPAE: Peer-Adaptive Ensemble Learning for Asynchronous and Model-Heterogeneous Federated Learning
Creators: Brianna Mueller - University of Iowa
W. Nick Street - University of Iowa
Stephen Baek - University of Virginia
Qihang Lin - University of Iowa
Jingyi Yang - New York University
Yankun Huang - Arizona State University
Resource Type: Preprint
Publication Details: ArXiv.org
DOI: 10.48550/arxiv.2410.14075
ISSN: 2331-8422
Publisher: Cornell University; Ithaca, New York
Language: English
Date posted: 10/17/2024
Academic Unit: Bus Admin College; Nursing; Computer Science; Business Analytics
Record Identifier: 9984738441402771

Metrics

12 Record Views