AdaptSFL: adaptive split federated learning in resource-constrained edge networks
File(s)
Accepted version
Author(s)
Leung, Kin
Lin, Zheng
Wei, Wei
Chen, Xianhao
Type
Journal Article
Abstract
The increasing complexity of deep neural networks poses significant barriers to democratizing AI to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution that enables device-server co-training through model splitting. However, although system optimization substantially influences the performance of SFL, the problem remains largely uncharted. In this paper, we first provide a unified convergence analysis of SFL, which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on its learning performance, laying a theoretical foundation for this field. Based on this convergence bound, we introduce AdaptSFL, an adaptive SFL framework to accelerate SFL under resource-constrained edge computing systems. Specifically, AdaptSFL adaptively controls MS and client-side MA to balance communication-computing latency and training convergence. Extensive simulations across various datasets validate that our proposed AdaptSFL framework takes considerably less time to achieve target accuracy than existing benchmarks.
Date Issued
2025-06-25
Date Acceptance
2025-06-04
Citation
IEEE ACM Transactions on Networking, 2025
ISSN
1063-6692
Publisher
Institute of Electrical and Electronics Engineers
Journal / Book Title
IEEE ACM Transactions on Networking
Copyright Statement
© 2025, IEEE. This is the author’s accepted manuscript made available under a CC-BY licence in accordance with Imperial’s Research Publications Open Access policy (www.imperial.ac.uk/oa-policy)
License URL
Publication Status
Published online
Date Publish Online
2025-06-25