Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

3-2025

Abstract

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multimodel aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch models. To mitigate catastrophic forgetting, the main server of MultiSFL selects multiple assistant devices for knowledge replay according to the training data distribution of each full branch model. Experimental results obtained from various non-IID and IID scenarios demonstrate that MultiSFL significantly outperforms conventional SFL methods by up to a 23.25\% test accuracy improvement.

Discipline

Artificial Intelligence and Robotics

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

Proceedings of the 39th AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence, Philadelphia, Pennsylvania, 2025 February 25 - March 4

First Page

914

Last Page

922

ISBN

9781577358978

Identifier

10.1609/aaai.v39i1.32076

Publisher

AAAI Press

City or Country

USA

Additional URL

https://doi.org/10.1609/aaai.v39i1.32076

Download

Share

COinS