EUVIMEDEUVIMED entdecken
Crossref

Federated Split Learning for Edge Intelligence in Resource-Constrained Wireless Networks

Huiqing Ao, Hui Tian, Wanli Ni

IEEE Transactions on Consumer Electronics · 2025-05 · 71 (2) · 4451-4463

DOI: 10.1109/tce.2024.3464731 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-05. Verfasst von Huiqing Ao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid advancement of the Internet of Things (IoT) and artificial intelligence has significantly increased the number of consumer electronics devices. Traditional federated learning methods typically require all these devices to collaboratively train deep neural networks (DNNs). However, this approach poses a significant challenge due to the substantial communication overhead incurred by uploading and downloading the large DNN models between the base station and resource-constrained IoT devices. To overcome this challenge, we propose a federated split learning (FedSL) framework, along with two variants (FedSL-I and FedSL-II). Furthermore, considering the limitations posed by battery capacity, heterogeneous channels and computing capabilities across all consumer devices, we jointly optimize power allocation, device scheduling and split layer selection to minimize the per-round weighted sum of training delay and energy consumption. We design alternating optimization algorithms to attain a sub-optimal solution with reduced computational complexity. Simulation results demonstrate that our proposed FedSL enables efficient collaborative model training among IoT devices, leading to a significant reduction in communication overhead, and ultimately enhancing the overall performance.

Förderung

  • Beijing Natural Science Foundation-Haidian Original Innovation Joint Fund

Zitieren

APA

Ao, H., Tian, H., & Ni, W. (2025). Federated Split Learning for Edge Intelligence in Resource-Constrained Wireless Networks. IEEE Transactions on Consumer Electronics, 71(2), 4451-4463. https://doi.org/10.1109/tce.2024.3464731

Vancouver

Ao H, Tian H, Ni W. Federated Split Learning for Edge Intelligence in Resource-Constrained Wireless Networks. IEEE Transactions on Consumer Electronics. 2025;71(2):4451-4463. doi:10.1109/tce.2024.3464731

BibTeX
@article{Ao2025,
  author = {Ao, Huiqing and Tian, Hui and Ni, Wanli},
  title = {Federated Split Learning for Edge Intelligence in Resource-Constrained Wireless Networks},
  journal = {IEEE Transactions on Consumer Electronics},
  year = {2025},
  volume = {71},
  number = {2},
  pages = {4451--4463},
  doi = {10.1109/tce.2024.3464731}
}
Kostenlos starten →