Adaptive Information Bottleneck Guided Joint Source-Channel Coding

Joint source channel coding (JSCC) has attracted increasing attentions due to its robustness and high efficiency. However, the existing research on JSCC mainly focuses on minimizing the distortion between the transmitted and received information, while limiting the required data rate. Therefore, even though the transmitted information is well recovered, the transmitted bits may be far more than the minimal threshold according to the rate-distortion (RD) theory. In this paper, we propose an adaptive Information Bottleneck (IB) guided JSCC (AIB-JSCC), which aims at achieving the theoretically maximal compression ratio for a given reconstruction quality. In particular, we first derive a mathematically tractable form of loss function for AIB-JSCC. To keep a better tradeoff between compression and reconstruction quality, we further propose an adaptive algorithm that adjusts hyperparameter beta of the proposed loss function dynamically according to the distortion during training. Experiment results show that AIB-JSCC can significantly reduce the required amount of the transmitted data and improve the reconstruction quality and downstream artificial-intelligent task performance.