Neural Communication Systems with Bandwidth-limited Channel

TL;DR

This paper explores neural communication systems over bandwidth-limited channels, proposing joint source and channel coding with neural networks, a differentiable channel model, and auxiliary variables, leading to improved transmission quality.

Contribution

It introduces a joint neural coding framework for bandwidth-limited channels, incorporating a differentiable channel model and auxiliary variables, advancing neural communication methods.

Findings

Joint coding outperforms separate coding with neural networks.

Differentiable bandwidth-limited channel facilitates learning.

Enhanced distortion and FID scores demonstrate improved performance.

Abstract

Reliably transmitting messages despite information loss due to a noisy channel is a core problem of information theory. One of the most important aspects of real world communication, e.g. via wifi, is that it may happen at varying levels of information transfer. The bandwidth-limited channel models this phenomenon. In this study we consider learning coding with the bandwidth-limited channel (BWLC). Recently, neural communication models such as variational autoencoders have been studied for the task of source compression. We build upon this work by studying neural communication systems with the BWLC. Specifically,we find three modelling choices that are relevant under expected information loss. First, instead of separating the sub-tasks of compression (source coding) and error correction (channel coding), we propose to model both jointly. Framing the problem as a variational learning problem, we conclude that joint systems outperform their separate counterparts when coding is performed by flexible learnable function approximators such as neural networks. To facilitate learning, we introduce a differentiable and computationally efficient version of the bandwidth-limited channel. Second, we propose a design to model missing information with a prior, and incorporate this into the channel model. Finally, sampling from the joint model is improved by introducing auxiliary latent variables in the decoder. Experimental results justify the validity of our design decisions through improved distortion and FID scores.