AdaptSFL: Adaptive Split Federated Learning in Resource-Constrained Edge Networks
IEEE Transactions on Networking · 2025-12 · 33 (6) · 2993-3008
DOI: 10.1109/ton.2025.3577790 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Networking, 2025-12. Verfasst von Zheng Lin und 4 weiteren Autor:innen. Die Arbeit wurde bisher 58-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: Research Grants Council of Hong Kong, University of Hong Kong (HKU) Institute of Data Science (IDS) Research Seed Fund, Engineering and Physical Sciences Research Council.
Abstract (Originalsprache)
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.
Förderung
- Research Grants Council of Hong Kong
- University of Hong Kong (HKU) Institute of Data Science (IDS) Research Seed Fund
- Engineering and Physical Sciences Research Council
Zitieren
APA
Lin, Z., Qu, G., Wei, W., Chen, X., & Leung, K. K. (2025). AdaptSFL: Adaptive Split Federated Learning in Resource-Constrained Edge Networks. IEEE Transactions on Networking, 33(6), 2993-3008. https://doi.org/10.1109/ton.2025.3577790
Vancouver
Lin Z, Qu G, Wei W, Chen X, Leung KK. AdaptSFL: Adaptive Split Federated Learning in Resource-Constrained Edge Networks. IEEE Transactions on Networking. 2025;33(6):2993-3008. doi:10.1109/ton.2025.3577790
BibTeX
@article{Lin2025,
author = {Lin, Zheng and Qu, Guanqiao and Wei, Wei and Chen, Xianhao and Leung, Kin K.},
title = {AdaptSFL: Adaptive Split Federated Learning in Resource-Constrained Edge Networks},
journal = {IEEE Transactions on Networking},
year = {2025},
volume = {33},
number = {6},
pages = {2993--3008},
doi = {10.1109/ton.2025.3577790}
}
EUVIMED