EUVIMEDEUVIMED entdecken
Crossref

AGH-MGC: A Unified Compression Training Framework for Interference Recognition Models in Satellite Communications

Yanan Liu, Yuanzhi He, Ziyao Zhou, Zheng Dou

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 13040-13051

DOI: 10.1109/tccn.2026.3742837 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Yanan Liu und 3 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The growing complexity of satellite communication systems demands lightweight deep models capable of efficient interference recognition under strict resource constraints. However, current compression training approaches face intrinsic challenges, including the non-differentiability of hard-mask pruning, the lack of adaptive sparsity control, and gradient interference between pruning and quantization. To overcome these limitations, this paper introduces a unified compression training framework with Adaptive Gradient Harmonization and Mask-Aware Gradient Compensation (AGH-MGC), which seamlessly integrates differentiable pruning, adaptive sparsity learning, and cooperative quantization. The framework leverages Gumbel–Softmax for differentiable structure selection, employs a swarm intelligence–based strategy to dynamically regulate sparsity, and adopts a coarse-to-fine quantization scheme to optimize error allocation. Moreover, an adaptive gradient harmonization mechanism is designed to mitigate gradient conflicts and stabilize joint optimization. Experimental results demonstrate that AGH-MGC achieves an overall compression ratio of up to 96.10% across four interference recognition models, while maintaining competitive accuracy and robust optimization stability. These findings highlight the framework’s potential as a general and effective solution for structured model compression in satellite communication systems.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Liu, Y., He, Y., Zhou, Z., & Dou, Z. (2026). AGH-MGC: A Unified Compression Training Framework for Interference Recognition Models in Satellite Communications. IEEE Transactions on Cognitive Communications and Networking, 12, 13040-13051. https://doi.org/10.1109/tccn.2026.3742837

Vancouver

Liu Y, He Y, Zhou Z, Dou Z. AGH-MGC: A Unified Compression Training Framework for Interference Recognition Models in Satellite Communications. IEEE Transactions on Cognitive Communications and Networking. 2026;12:13040-13051. doi:10.1109/tccn.2026.3742837

BibTeX
@article{Liu2026,
  author = {Liu, Yanan and He, Yuanzhi and Zhou, Ziyao and Dou, Zheng},
  title = {AGH-MGC: A Unified Compression Training Framework for Interference Recognition Models in Satellite Communications},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {13040--13051},
  doi = {10.1109/tccn.2026.3742837}
}
Kostenlos starten →