Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks
IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 22835-22848
DOI: 10.1109/tmc.2026.3727683 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Fei Teng und 6 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: NSFC, China Postdoctoral Science Foundation, Postdoctoral Fellowship Program of CPSF.
Abstract (Originalsprache)
Artificial intelligence (AI) has significantly advanced satellite imagery applications, but it confronts critical communication limitations from LEO satellites’ high mobility. Satellite-ground federated learning (SGFL) provides a promising approach to enabling satellites to collaboratively train shared models, with ground stations orchestrating global aggregation. However, LEO satellite networks exhibit fundamentally distinct packet loss patterns compared to terrestrial networks, characterized by: (i) significant asymmetry, (ii) high burstiness, and (iii) heavy-tailed distribution, which largely degrades SGFL’s communication efficiency. In this work, we propose a UDP-based SGFL framework that strategically discards lost parameters to improve network throughput. To overcome the above challenges, we introduce the Zero-inflated Beta Regression model to fit the uplink (ground-to-satellite) packet loss distribution in satellite-ground communications. Then, we transform the end-to-end FL workflow into a time-minimization task scheduling problem. Finally, We design an Overlapped Block-wise Scheduling framework that allows on-satellite training to run in parallel with model downloading, greatly reducing the total completion time of each FL round. Extensive evaluations demonstrate a 20.5× speedup in end-to-end SGFL training with negligible accuracy loss.
Förderung
- NSFC
- China Postdoctoral Science Foundation
- Postdoctoral Fellowship Program of CPSF
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Teng, F., Mou, S., Yang, C., Yuan, J., Zhang, Q., Lin, Z., & Ni, W. (2026). Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks. IEEE Transactions on Mobile Computing, 25(12), 22835-22848. https://doi.org/10.1109/tmc.2026.3727683
Vancouver
Teng F, Mou S, Yang C, Yuan J, Zhang Q, Lin Z, et al. Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks. IEEE Transactions on Mobile Computing. 2026;25(12):22835-22848. doi:10.1109/tmc.2026.3727683
BibTeX
@article{Teng2026,
author = {Teng, Fei and Mou, Sijing and Yang, Chen and Yuan, Jinliang and Zhang, Qiyang and Lin, Zheng and Ni, Wei},
title = {Communication-Efficient Satellite-Ground Federated Learning Over Intermittent LEO Satellite Networks},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {12},
pages = {22835--22848},
doi = {10.1109/tmc.2026.3727683}
}
EUVIMED