Knowledge Distillation Based Semantic Communications For Multiple Users
This work addresses robustness and efficiency issues in semantic communications for multiple users, representing an incremental advancement by applying knowledge distillation to enhance existing deep learning methods.
The paper tackles the problem of limited model generalizability and complexity in semantic communication systems with multiple users under unexpected interference and few training samples, proposing a knowledge distillation-based system that improves robustness and generalization while reducing performance loss during model compression, with numerical results showing significant improvements.
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.