EUVIMEDEUVIMED entdecken
Crossref

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

Mingxiong Zhao, Shihao Zhao, Chenyuan Feng, Howard H. Yang, Dusit Niyato, Tony Q. S. Quek

IEEE Internet of Things Journal · 15.06.2025 · 12 (12) · 18692-18707

DOI: 10.1109/jiot.2025.3554759 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Internet of Things Journal, erschienen am 15.06.2025. Verfasst von Mingxiong Zhao und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Applied Basic Research Foundation of Yunnan Province, Opening Foundation of Yunnan Key Laboratory of Smart City in Cyberspace Security.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an autonomous aerial vehicle (AAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a AAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by AAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different AAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed semi-synchronous FL with cross-sharpness and layer-freezing (SFedXL), tailored for a AAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a tradeoff of increased local computation latency.

Förderung

  • National Natural Science Foundation of China
  • Applied Basic Research Foundation of Yunnan Province
  • Opening Foundation of Yunnan Key Laboratory of Smart City in Cyberspace Security
  • Innovation Foundation of Engineering Research Center of Integration and Application of Digital Learning Technology, Ministry of Education, China
  • Foundation of Yunnan Key Laboratory of Service Computing
  • National Research Foundation Singapore
  • Infocomm Media Development Authority under its Future Communications Research and Development Programme

Zitieren

APA

Zhao, M., Zhao, S., Feng, C., Yang, H. H., Niyato, D., & Quek, T. Q. S. (2025). SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing. IEEE Internet of Things Journal, 12(12), 18692-18707. https://doi.org/10.1109/jiot.2025.3554759

Vancouver

Zhao M, Zhao S, Feng C, Yang HH, Niyato D, Quek TQS. SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing. IEEE Internet of Things Journal. 2025;12(12):18692-18707. doi:10.1109/jiot.2025.3554759

BibTeX
@article{Zhao2025,
  author = {Zhao, Mingxiong and Zhao, Shihao and Feng, Chenyuan and Yang, Howard H. and Niyato, Dusit and Quek, Tony Q. S.},
  title = {SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing},
  journal = {IEEE Internet of Things Journal},
  year = {2025},
  volume = {12},
  number = {12},
  pages = {18692--18707},
  doi = {10.1109/jiot.2025.3554759}
}
Kostenlos starten →