首页|GAI-Enhanced Robust Semantic Communication With Asymmetric Architecture

GAI-Enhanced Robust Semantic Communication With Asymmetric Architecture

扫码查看
原文链接
  • NETL
  • NSTL
  • IEEE
Semantic communication (SC), regarded as a next-generation communication architecture that breaks through the Shannon paradigm, is considered a key technology for realizing future sixth-generation wireless networks and cognitive communications. Instead of focusing on the bit error rate, SC is dedicated to extracting abstract semantic information from original data to enhance communication efficiency for specific tasks. However, current SC systems mostly rely on symmetric architectures based on convolutional neural networks, which not only severely limits the capacity of the network but also leads to a high degree of coupling between the encoder and decoder. Additionally, it also lacks robustness in noise reference. The emergence of generative artificial intelligence (GAI) breaks this bottleneck. In this paper, we propose an asymmetric end-to-end SC architecture based on GAI, named masked joint source-channel coding (M-JSCC). In our model, the encoder serves as a universal semantic extractor, while the decoder is tailored to specific tasks. During the model training, we introduce a masking mechanism that improves the performance of M-JSCC to extract semantic information and enhances the robustness under various channel conditions. Moreover, it also endows M-JSCC with remarkable data generation abilities. Benefiting from the asymmetric architecture, the decoder no longer depends on the encoder, which allows it to be switched according to the specific requirements to better adapt to different task-oriented scenarios. Finally, comprehensive experiments demonstrate the excellent semantic understanding and communication robustness of M-JSCC.

SemanticsDecodingData miningSignal to noise ratioImage reconstructionChannel codingRobustnessAdaptation modelsTrainingData models

Pengfei Ren、Jingjing Wang、Xiangwang Hou、Jianrui Chen、Chunxiao Jiang

展开 >

School of Cyber Science and Technology, Beihang University, Beijing, China|Hangzhou Innovation Institute, Beihang University, Hangzhou, China

Department of Electronic Engineering, Tsinghua University, Beijing, China

School of Cyber Science and Technology, Beihang University, Beijing, China|Peng Cheng Laboratory, Shenzhen, China

Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China

展开 >

2025

10.1109/TCCN.2024.3520132

IEEE transactions on cognitive communications and networking

IEEE transactions on cognitive communications and networking

ISSN：
年,卷(期)：2025.11(2)
  • 46