Channel-Aware Deep Joint Source-Channel Coding for Multi-Task Oriented Semantic Communication

Existing deep learning (DL)-based semantic communication generally employs deep neural networks (DNNs) for semantic extraction at a fixed dimension and incorporates channel state information (CSI) to facilitate semantic transmission. However, the optimal dimension of the semantic information to tran...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE wireless communications letters Jg. 14; H. 5; S. 1521 - 1525
Hauptverfasser: Wang, Biqi, Gu, Run, Xu, Wei, Jiang, Feng, Li, Mengyu, Wang, Shen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.05.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial neural networks
Coding
Communication
Data mining
Decoding
deep learning
Feature extraction
Image reconstruction
joint source and channel coding
Machine learning
multi-task execution
Multitasking
Optimization
Reference signals
Semantic communication
Semantics
Signal to noise ratio
Training
Vectors
Visualization
Wireless communications
ISSN:2162-2337, 2162-2345
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Existing deep learning (DL)-based semantic communication generally employs deep neural networks (DNNs) for semantic extraction at a fixed dimension and incorporates channel state information (CSI) to facilitate semantic transmission. However, the optimal dimension of the semantic information to transmit varies with wireless channel conditions, trading off between channel uses and performance depending on the channel condition. To strike the balance, this letter proposes a channel-aware deep joint source-channel coding (CA-DJSCC) for multi-task oriented semantic communication. Specifically, we formulate an optimization problem to characterize the intricate and hard-to-quantify relationship between the channel condition and the optimal dimension. To achieve the channel-adaptive dimension, we develop a joint source and channel encoder, pruning elements based on semantic importance. Correspondingly, we also design a joint source and channel decoder, introducing a reference signal to enhance the multi-task performance. Simulation results demonstrate that the CA-DJSCC achieves superior performance in terms of both image reconstruction and classification tasks, with over 44.1% reduction in average channel uses compared to typical baselines.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2162-2337
2162-2345
DOI:10.1109/LWC.2025.3548084