EUVIMEDEUVIMED entdecken
Crossref

Adaptive Incentivize for Federated Learning With Cloud-Edge Collaboration Under Multi-Level Information Sharing

Shijing Yuan, Beiyu Dong, Jie Li, Song Guo, Hongyang Chen, Chentao Wu, Jie Wu, Wei Zhao

IEEE Transactions on Computers · 2025-07 · 74 (7) · 2445-2460

DOI: 10.1109/tc.2025.3566864 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Computers, 2025-07. Verfasst von Shijing Yuan und 7 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Hong Kong RGC General Research Fund, Research Impact Fund, Collaborative Research Fund.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated Learning with Cloud-Edge Collaboration (FL-CEC) has emerged as a cutting-edge paradigm in distributed learning. Efficient resource investment incentive mechanisms are crucial to encouraging clients in FL-CEC to contribute the necessary data and computational resources for training. However, existing studies are inadequate in meeting the incentive design requirements under multi-level information-sharing scenarios. Moreover, current works often rely on specific functional relationships between resource investment and global model accuracy. To bridge these gaps, this paper investigates the incentive problem for data and computational resource investment under multi-level information-sharing levels. We design a resource investment incentive mechanism based on a weighted potential game without depending on any specific functional relationship between data investment and model accuracy. Furthermore, we propose four algorithms to solve resource investment strategies for different levels of information sharing. The complexity and convergence rates of the proposed algorithms are thoroughly analyzed. Finally, we construct a simulation incentive platform on Aliyun. Extensive evaluations demonstrate that the proposed scheme effectively enhances social welfare, and improves collaborative training accuracy and efficiency.

Förderung

  • Hong Kong RGC General Research Fund
  • Research Impact Fund
  • Collaborative Research Fund
  • NSFC/RGC Collaborative Research Scheme
  • Areas of Excellence Scheme
  • National Natural Science Foundation of China
  • Research and Development Program of China Telecom

Zitieren

APA

Yuan, S., Dong, B., Li, J., Guo, S., Chen, H., Wu, C., Wu, J., & Zhao, W. (2025). Adaptive Incentivize for Federated Learning With Cloud-Edge Collaboration Under Multi-Level Information Sharing. IEEE Transactions on Computers, 74(7), 2445-2460. https://doi.org/10.1109/tc.2025.3566864

Vancouver

Yuan S, Dong B, Li J, Guo S, Chen H, Wu C, et al. Adaptive Incentivize for Federated Learning With Cloud-Edge Collaboration Under Multi-Level Information Sharing. IEEE Transactions on Computers. 2025;74(7):2445-2460. doi:10.1109/tc.2025.3566864

BibTeX
@article{Yuan2025,
  author = {Yuan, Shijing and Dong, Beiyu and Li, Jie and Guo, Song and Chen, Hongyang and Wu, Chentao and Wu, Jie and Zhao, Wei},
  title = {Adaptive Incentivize for Federated Learning With Cloud-Edge Collaboration Under Multi-Level Information Sharing},
  journal = {IEEE Transactions on Computers},
  year = {2025},
  volume = {74},
  number = {7},
  pages = {2445--2460},
  doi = {10.1109/tc.2025.3566864}
}
Kostenlos starten →