EUVIMEDEUVIMED entdecken
Crossref

Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning

Lei Cheng, Gang Feng, Shuang Qin, Yao Sun, Jian Wang, Feng Wang, Tony Q. S. Quek

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 1211-1226

DOI: 10.1109/tccn.2025.3579527 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Lei Cheng und 6 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic Research Funds for Central Universities of China, Natural Science Foundation of Sichuan Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The significant enhancement of satellite onboard processing capability and drastic proliferation of Artificial Intelligence (AI) applications have fostered decentralized satellite federated learning (DSFL), a transformative paradigm that exchanges and aggregates machine learning (ML) models in satellite clusters for collaborative learning. However, the limited model exchange opportunities caused by intermittent inter-satellite contacts, along with heterogeneous onboard datasets, can lead to ineffective and/or biased model aggregation. To address these issues, it is crucial yet challenging to design an effective DSFL scheduling strategy that determines whether and when to pull models from contact satellites and perform local training for optimizing DSFL performance. In this paper, we propose a contact-based DSFL framework and formulate the DSFL scheduling problem to maximize the accuracy of trained models. As the problem cannot be solved directly, we transform it into a hierarchical Markov game by introducing options for decision agents deployed on individual satellites. Under a learning-to-learn paradigm, we develop a Multi-agent Dueling Double Deep Q Network (MA3DQN)-based intelligent DSFL scheduling strategy. The agents, trained in a distributed and alternating manner, adaptively make scheduling decisions based on instantaneous partial observations of the environment. Simulation results demonstrate the efficiency and adaptability of the MA3DQN-based strategy over three baselines.

Förderung

  • National Natural Science Foundation of China
  • Basic Research Funds for Central Universities of China
  • Natural Science Foundation of Sichuan Province
  • National Research Foundation, Singapore and Infocomm Media Development Authority under its Future Communications Research & Development Programme

Zitieren

APA

Cheng, L., Feng, G., Qin, S., Sun, Y., Wang, J., Wang, F., & Quek, T. Q. S. (2026). Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning. IEEE Transactions on Cognitive Communications and Networking, 12, 1211-1226. https://doi.org/10.1109/tccn.2025.3579527

Vancouver

Cheng L, Feng G, Qin S, Sun Y, Wang J, Wang F, et al. Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning. IEEE Transactions on Cognitive Communications and Networking. 2026;12:1211-1226. doi:10.1109/tccn.2025.3579527

BibTeX
@article{Cheng2026,
  author = {Cheng, Lei and Feng, Gang and Qin, Shuang and Sun, Yao and Wang, Jian and Wang, Feng and Quek, Tony Q. S.},
  title = {Scheduling Model Transmission and Training for Contact-Based Decentralized Satellite Federated Learning},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {1211--1226},
  doi = {10.1109/tccn.2025.3579527}
}
Kostenlos starten →