Learning Multi-Rate Task-Oriented Communications Over Symmetric Discrete Memoryless Channels
IEEE Communications Letters · 2024-10 · 28 (10) · 2303-2307
DOI: 10.1109/lcomm.2024.3450598 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2024-10. Verfasst von Anbang Zhang und 1 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 15 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Shandong Province, Taishan Young Scholar.
Abstract (Originalsprache)
This letter introduces a multi-rate task-oriented communication (MR-ToC) framework. This framework dynamically adapts to variations in affordable data rate within the communication pipeline. It conceptualizes communication pipelines as symmetric, discrete, memoryless channels. We employ a progressive learning strategy to train the system, comprising a nested codebook for encoding and task inference. This configuration allows for the adjustment of multiple rate levels in response to evolving channel conditions. The results from our experiments show that this system not only supports edge inference across various coding levels but also excels in adapting to variable communication environments.
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Shandong Province
- Taishan Young Scholar
- Major Scientific and Technological Innovation Project of Shandong Province
Zitieren
APA
Zhang, A., & Guo, S. (2024). Learning Multi-Rate Task-Oriented Communications Over Symmetric Discrete Memoryless Channels. IEEE Communications Letters, 28(10), 2303-2307. https://doi.org/10.1109/lcomm.2024.3450598
Vancouver
Zhang A, Guo S. Learning Multi-Rate Task-Oriented Communications Over Symmetric Discrete Memoryless Channels. IEEE Communications Letters. 2024;28(10):2303-2307. doi:10.1109/lcomm.2024.3450598
BibTeX
@article{Zhang2024,
author = {Zhang, Anbang and Guo, Shuaishuai},
title = {Learning Multi-Rate Task-Oriented Communications Over Symmetric Discrete Memoryless Channels},
journal = {IEEE Communications Letters},
year = {2024},
volume = {28},
number = {10},
pages = {2303--2307},
doi = {10.1109/lcomm.2024.3450598}
}
EUVIMED