Learning End-to-End Channel Coding with Diffusion Models

TL;DR

This paper explores the use of diffusion models for end-to-end channel coding in wireless communications, demonstrating they perform comparably to GANs but with more stable training and better generalization.

Contribution

It introduces diffusion models as a novel approach for channel generation in E2E systems, offering improved stability and generalization over existing generative methods.

Findings

Diffusion models match GAN performance in channel generation.

Diffusion models exhibit more stable training processes.

Diffusion models generalize better in testing scenarios.

Abstract

It is a known problem that deep-learning-based end-to-end (E2E) channel coding systems depend on a known and differentiable channel model, due to the learning process and based on the gradient-descent optimization methods. This places the challenge to approximate or generate the channel or its derivative from samples generated by pilot signaling in real-world scenarios. Currently, there are two prevalent methods to solve this problem. One is to generate the channel via a generative adversarial network (GAN), and the other is to, in essence, approximate the gradient via reinforcement learning methods. Other methods include using score-based methods, variational autoencoders, or mutual-information-based methods. In this paper, we focus on generative models and, in particular, on a new promising method called diffusion models, which have shown a higher quality of generation in image-based tasks. We will show that diffusion models can be used in wireless E2E scenarios and that they work as good as Wasserstein GANs while having a more stable training procedure and a better generalization ability in testing.