EUVIMEDEUVIMED entdecken
Crossref

LEO-Split: A Semi-Supervised Split Learning Framework Over LEO Satellite Networks

Zheng Lin, Yuxin Zhang, Zhe Chen, Zihan Fang, Cong Wu, Xianhao Chen, Yue Gao, Jun Luo

IEEE Transactions on Mobile Computing · 2026-02 · 25 (2) · 1565-1579

DOI: 10.1109/tmc.2025.3601371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-02. Verfasst von Zheng Lin und 7 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: Natural Science Foundation of Shanghai, National Key R&D Program of China, Research Grants Council of Hong Kong.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, the increasing deployment of LEO satellite systems has enabled various space analytics (e.g., crop and climate monitoring), which heavily relies on the advancements in deep learning (DL). However, the intermittent connectivity between LEO satellites and ground station (GS) significantly hinders the timely transmission of raw data to GS for centralized learning, while the scaled-up DL models hamper distributed learning on resource-constrained LEO satellites. Though split learning (SL) can be a potential solution to these problems by partitioning a model and offloading primary training workload to GS, the labor-intensive labeling process remains an obstacle, with intermittent connectivity and data heterogeneity being other challenges. In this paper, we propose LEO-Split, a semi-supervised (SS) SL design tailored for satellite networks to combat these challenges. Leveraging SS learning to handle (labeled) data scarcity, we construct an auxiliary model to tackle the training failure of the satellite-GS non-contact time. Moreover, we propose a pseudo-labeling algorithm to rectify data imbalances across satellites. Lastly, an adaptive activation interpolation scheme is devised to prevent the overfitting of server-side sub-model training at GS. Extensive experiments with real-world LEO satellite traces (e.g., Starlink) demonstrate that our LEO-Split framework achieves superior performance compared to state-of-the-art benchmarks.

Förderung

  • Natural Science Foundation of Shanghai
  • National Key R&D Program of China
  • Research Grants Council of Hong Kong
  • HKU IDS Research Seed Fund

Zitieren

APA

Lin, Z., Zhang, Y., Chen, Z., Fang, Z., Wu, C., Chen, X., Gao, Y., & Luo, J. (2026). LEO-Split: A Semi-Supervised Split Learning Framework Over LEO Satellite Networks. IEEE Transactions on Mobile Computing, 25(2), 1565-1579. https://doi.org/10.1109/tmc.2025.3601371

Vancouver

Lin Z, Zhang Y, Chen Z, Fang Z, Wu C, Chen X, et al. LEO-Split: A Semi-Supervised Split Learning Framework Over LEO Satellite Networks. IEEE Transactions on Mobile Computing. 2026;25(2):1565-1579. doi:10.1109/tmc.2025.3601371

BibTeX
@article{Lin2026,
  author = {Lin, Zheng and Zhang, Yuxin and Chen, Zhe and Fang, Zihan and Wu, Cong and Chen, Xianhao and Gao, Yue and Luo, Jun},
  title = {LEO-Split: A Semi-Supervised Split Learning Framework Over LEO Satellite Networks},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {2},
  pages = {1565--1579},
  doi = {10.1109/tmc.2025.3601371}
}
Kostenlos starten →