GAI-Enhanced Robust Semantic Communication With Asymmetric Architecture

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.