Knowledge Distillation Based Semantic Communications For Multiple Users

Liu, Chenguang; Zhou, Yuxin; Chen, Yunfei; Yang, Shuang-Hua

Abstract

Deep learning (DL) has shown great potential in revolutionizing the traditional communications system. Many applications in communications have adopted DL techniques due to their powerful representation ability. However, the learning-based methods can be dependent on the training dataset and perform worse on unseen interference due to limited model generalizability and complexity. In this paper, we consider the semantic communication (SemCom) system with multiple users, where there is a limited number of training samples and unexpected interference. To improve the model generalization ability and reduce the model size, we propose a knowledge distillation (KD) based system where Transformer based encoder-decoder is implemented as the semantic encoder-decoder and fully connected neural networks are implemented as the channel encoder-decoder. Specifically, four types of knowledge transfer and model compression are analyzed. Important system and model parameters are considered, including the level of noise and interference, the number of interfering users and the size of the encoder and decoder. Numerical results demonstrate that KD significantly improves the robustness and the generalization ability when applied to unexpected interference, and it reduces the performance loss when compressing the model size.

Citation

Liu, C., Zhou, Y., Chen, Y., & Yang, S.-H. (online). Knowledge Distillation Based Semantic Communications For Multiple Users. IEEE Transactions on Wireless Communications, 23(7), 7000-7012. https://doi.org/10.1109/TWC.2023.3336941

• Journal Article Type: Article
• Acceptance Date: Nov 22, 2023
• Online Publication Date: Dec 5, 2023
• Deposit Date: Nov 23, 2023
• Publicly Available Date: Dec 5, 2023
• Journal: IEEE Transactions on Wireless Communications
• Print ISSN: 1536-1276
• Electronic ISSN: 1558-2248
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Volume: 23
• Issue: 7
• Pages: 7000-7012
• DOI: https://doi.org/10.1109/TWC.2023.3336941
• Public URL: https://durham-repository.worktribe.com/output/1948142