EUVIMEDEUVIMED entdecken
Crossref

FedCLR+: Tackling Onboard Label Constraints for Accurate Federated Satellite Computing

Chen Yang, Qiyang Zhang, Qibo Sun, Shufeng Ouyang, Ao Zhou, Shangguang Wang, Mengwei Xu

IEEE Transactions on Services Computing · 2025-07 · 18 (4) · 2075-2088

DOI: 10.1109/tsc.2025.3583150 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Services Computing, 2025-07. Verfasst von Chen Yang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 49 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The rapid growth of Low Earth Orbit (LEO) satellites, particularly with the increasing deployment of intelligent computing capabilities using commercial off-the-shelf (COTS) hardware, presents significant opportunities to enhance the quality of in-orbit services. However, the current onboard conditions remain insufficient to enhance model accuracy by increasing model size, and inadequate accuracy hampers the effectiveness of in-orbit services. The satellite-ground federated learning (FL) paradigm, leveraging collaborative fine-tuning, offers a promising solution to continuously improve onboard model performance. Prior studies have focused on optimizing fine-tuning under constraints like limited bandwidth and computational resources, they often overlook two critical challenges: the scarcity and skewness of labeled onboard data and the long revisit cycles of satellites. To address these challenges and better support in-orbit services, this article designs a realistic simulation methodology for the onboard fine-tuning process and conducts a comprehensive measurement study. Based on insights from the measurement results, we propose an efficient satellite-ground federated fine-tuning system, FedCLR+. In this system, we design a FedCLR algorithm to enhance system accuracy through representation optimization. Additionally, we propose a hybrid bias-compensated strategy to further mitigate accuracy loss by enriching the diversity of aggregation information. Experimental results show that FedCLR+ significantly enhances accuracy by up to 21.61×, reduces transmission volume by an average of 7.29%, and maintaining acceptable additional overhead compared to baselines.

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Yang, C., Zhang, Q., Sun, Q., Ouyang, S., Zhou, A., Wang, S., & Xu, M. (2025). FedCLR+: Tackling Onboard Label Constraints for Accurate Federated Satellite Computing. IEEE Transactions on Services Computing, 18(4), 2075-2088. https://doi.org/10.1109/tsc.2025.3583150

Vancouver

Yang C, Zhang Q, Sun Q, Ouyang S, Zhou A, Wang S, et al. FedCLR+: Tackling Onboard Label Constraints for Accurate Federated Satellite Computing. IEEE Transactions on Services Computing. 2025;18(4):2075-2088. doi:10.1109/tsc.2025.3583150

BibTeX
@article{Yang2025,
  author = {Yang, Chen and Zhang, Qiyang and Sun, Qibo and Ouyang, Shufeng and Zhou, Ao and Wang, Shangguang and Xu, Mengwei},
  title = {FedCLR+: Tackling Onboard Label Constraints for Accurate Federated Satellite Computing},
  journal = {IEEE Transactions on Services Computing},
  year = {2025},
  volume = {18},
  number = {4},
  pages = {2075--2088},
  doi = {10.1109/tsc.2025.3583150}
}
Kostenlos starten →