EUVIMEDEUVIMED entdecken
Crossref

Large-Scale Model-Enabled Semantic Communication via Robust Knowledge Distillation and Lightweight Architecture Search

Kuiyuan Ding, Caili Guo, Yang Yang, Zhongtian Du, Walid Saad

IEEE Transactions on Cognitive Communications and Networking · 2026 · 12 · 7716-7730

DOI: 10.1109/tccn.2026.3687590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Cognitive Communications and Networking, 2026. Verfasst von Kuiyuan Ding und 4 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-scale models (LSMs) can be an effective framework for semantic representation and understanding, thereby providing a suitable tool for designing semantic communication (SC) systems. However, their direct deployment is often hindered by high computational complexity and resource requirements. In this paper, a novel robust knowledge distillation based semantic communication (RKD-SC) framework is proposed to enable efficient and channel-noise-robust LSM-powered SC. The framework addresses two key challenges: determining optimal compact model architectures and effectively transferring knowledge while maintaining robustness against channel noise. First, a knowledge distillation-based lightweight differentiable architecture search (KDL-DARTS) algorithm is proposed. This algorithm integrates knowledge distillation loss and a complexity penalty into the neural architecture search process to identify high-performance, lightweight semantic encoder architectures. Second, a novel two-stage robust knowledge distillation (RKD) algorithm is developed to transfer semantic capabilities from an LSM (teacher) to a compact encoder (student) and subsequently enhance system robustness. To further improve resilience to channel impairments, a channel-aware transformer (CAT) block is introduced as the channel codec, trained under diverse channel conditions with variable-length outputs. Extensive simulations on image classification tasks demonstrate that the RKD-SC framework significantly reduces model parameters while preserving a high degree of the teacher model’s performance and exhibiting superior robustness compared to existing methods.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Ding, K., Guo, C., Yang, Y., Du, Z., & Saad, W. (2026). Large-Scale Model-Enabled Semantic Communication via Robust Knowledge Distillation and Lightweight Architecture Search. IEEE Transactions on Cognitive Communications and Networking, 12, 7716-7730. https://doi.org/10.1109/tccn.2026.3687590

Vancouver

Ding K, Guo C, Yang Y, Du Z, Saad W. Large-Scale Model-Enabled Semantic Communication via Robust Knowledge Distillation and Lightweight Architecture Search. IEEE Transactions on Cognitive Communications and Networking. 2026;12:7716-7730. doi:10.1109/tccn.2026.3687590

BibTeX
@article{Ding2026,
  author = {Ding, Kuiyuan and Guo, Caili and Yang, Yang and Du, Zhongtian and Saad, Walid},
  title = {Large-Scale Model-Enabled Semantic Communication via Robust Knowledge Distillation and Lightweight Architecture Search},
  journal = {IEEE Transactions on Cognitive Communications and Networking},
  year = {2026},
  volume = {12},
  pages = {7716--7730},
  doi = {10.1109/tccn.2026.3687590}
}
Kostenlos starten →