Rateless Deep Joint Source-Channel Coding for Task-Oriented Image Communications
IEEE Transactions on Communications · 2026 · 74 · 8237-8253
DOI: 10.1109/tcomm.2026.3681652 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2026. Verfasst von Zijun Qin und 6 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Gefördert von: Beijing Natural Science Foundation, Beijing Natural Science Foundation Haidian Original Innovation Joint Fund Project, Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu.
Abstract (Originalsprache)
The advance of vehicle-to-everything (V2X) networks has led to many emerging data-intensive applications at the network edge. To meet the soaring data rate requirements of these applications, numerous coding schemes have been developed. However, the high heterogeneity of edge users brings challenges to these methods, including adaptation to performance requirements, coping with unknown or varying channels, as well as inefficient multicasting. In this paper, we address those problems by developing a rateless deep joint source-channel coding scheme featuring fine-grained control over rate and informativeness at the user. Towards this end, we first design a novel class of variational information bottleneck (VIB) by employing the multinomial-Gaussian (MG) distribution, to achieve rateless transmission over an erasure channel. We derive important results on the statistical properties of this latent distribution to facilitate efficient training of MG-VIB. Then, we apply this framework to multicasting, proposing MG-VIB-M to enhance adaptability and scalability. Simulations show that our proposed method is more flexible regarding rate-relevance tradeoffs, has greater robustness against channel imperfections, and reduces bandwidth requirements for task-oriented multicasting.
Förderung
- Beijing Natural Science Foundation
- Beijing Natural Science Foundation Haidian Original Innovation Joint Fund Project
- Natural Science Foundation on Frontier Leading Technology Basic Research Project of Jiangsu
- National Natural Science Foundation of China
- NSFC project
Zitieren
APA
Qin, Z., Fei, Z., Huang, J., Wang, J., Chen, X., Zhang, Z., & Xiao, M. (2026). Rateless Deep Joint Source-Channel Coding for Task-Oriented Image Communications. IEEE Transactions on Communications, 74, 8237-8253. https://doi.org/10.1109/tcomm.2026.3681652
Vancouver
Qin Z, Fei Z, Huang J, Wang J, Chen X, Zhang Z, et al. Rateless Deep Joint Source-Channel Coding for Task-Oriented Image Communications. IEEE Transactions on Communications. 2026;74:8237-8253. doi:10.1109/tcomm.2026.3681652
BibTeX
@article{Qin2026,
author = {Qin, Zijun and Fei, Zesong and Huang, Jingxuan and Wang, Jing and Chen, Xianhao and Zhang, Zhi and Xiao, Ming},
title = {Rateless Deep Joint Source-Channel Coding for Task-Oriented Image Communications},
journal = {IEEE Transactions on Communications},
year = {2026},
volume = {74},
pages = {8237--8253},
doi = {10.1109/tcomm.2026.3681652}
}
EUVIMED