Knowledge Distillation Based Semantic Communications For Multiple Users

TL;DR

This paper introduces a knowledge distillation approach for multi-user semantic communication systems using Transformer-based encoders and decoders, enhancing robustness and reducing model size amidst interference and limited training data.

Contribution

It proposes a novel KD-based semantic communication framework with Transformer models, analyzing four knowledge transfer types to improve generalization and compression.

Findings

KD improves robustness against interference

Model compression reduces performance loss

Enhanced generalization with limited training data

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.