EUVIMEDEUVIMED entdecken
Crossref

Noise-Resilient Semantic Communication via Frequency-Decoupled Quantization

Zhiyuan Xi, Kun Zhu, Yuanyuan Xu, Dusit Niyato

IEEE Transactions on Mobile Computing · 2026-08 · 25 (8) · 13246-13260

DOI: 10.1109/tmc.2026.3673321 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-08. Verfasst von Zhiyuan Xi und 3 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Semantic communication has emerged as a promising paradigm in next-generation communication systems, leveraging advanced artificial intelligence (AI) models to extract and transmit semantic representations for efficient information exchange. However, the reliability of received information is often compromised by unpredictable semantic noise, such as corruptions or distortions in the transmitted representations. Traditional methods typically rely on adversarial training with artificially injected noise to improve robustness. Yet, these approaches suffer from limited adaptability to varying noise conditions and incur considerable computational overhead during training. To address these challenges, this paper introduces Semantic communication with High-and-Low Frequency Decomposition (Se-HiLo), a novel noise-resilient scheme designed for image transmission. Se-HiLo integrates a Finite Scalar Quantization (FSQ) module that enhances robustness by constraining encoded representations within predefined discrete spaces, thereby eliminating the need for adversarial training. While FSQ strengthens resistance to noise, it inherently limits representational expressiveness. To mitigate this trade-off, Se-HiLo further incorporates a transformer-based high-and-low frequency decomposition module that separates image representations into distinct frequency components and encodes them into independent FSQ spaces, thus preserving semantic diversity and expressiveness. Extensive experiments validate that Se-HiLo significantly improves noise robustness and maintains accurate semantic communication across a wide range of noise environments.

Förderung

  • Fundamental Research Funds for the Central Universities

Zitieren

APA

Xi, Z., Zhu, K., Xu, Y., & Niyato, D. (2026). Noise-Resilient Semantic Communication via Frequency-Decoupled Quantization. IEEE Transactions on Mobile Computing, 25(8), 13246-13260. https://doi.org/10.1109/tmc.2026.3673321

Vancouver

Xi Z, Zhu K, Xu Y, Niyato D. Noise-Resilient Semantic Communication via Frequency-Decoupled Quantization. IEEE Transactions on Mobile Computing. 2026;25(8):13246-13260. doi:10.1109/tmc.2026.3673321

BibTeX
@article{Xi2026,
  author = {Xi, Zhiyuan and Zhu, Kun and Xu, Yuanyuan and Niyato, Dusit},
  title = {Noise-Resilient Semantic Communication via Frequency-Decoupled Quantization},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2026},
  volume = {25},
  number = {8},
  pages = {13246--13260},
  doi = {10.1109/tmc.2026.3673321}
}
Kostenlos starten →