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:10.1109/BigData62323.2024.10825304

Back

Conference proceeding

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

IEEE International Conference on Big Data (Print), pp.7961-7970

12/15/2024

DOI: 10.1109/BigData62323.2024.10825304

View Online

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.

decentralized learning

Ensemble learning

Federated learning

Medical services

model-heterogeneous federated learning

Peer-to-peer computing

personalized federated learning

Privacy

Robustness

Scalability

Soft sensors

Synchronization

Training

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: Conference proceeding
Publication Details: IEEE International Conference on Big Data (Print), pp.7961-7970
Publisher: IEEE
DOI: 10.1109/BigData62323.2024.10825304
eISSN: 2573-2978
Number of pages: 10
Language: English
Date published: 12/15/2024
Academic Unit: Nursing; Business Analytics; Computer Science; Bus Admin College
Record Identifier: 9984775269602771

Metrics

4 Record Views