Residual-Aided End-to-End Learning of Communication System without Known Channel

TL;DR

This paper introduces a residual-aided GAN (RA-GAN) training scheme for end-to-end communication systems that do not require known channels, effectively addressing gradient vanishing and overfitting issues to improve performance.

Contribution

The paper proposes a novel residual generator within GANs and a regularized loss function to enhance training stability and performance in channel imitation for communication systems.

Findings

RA-GAN outperforms conventional generators in generation quality.

The proposed scheme achieves near-optimal BLER performance.

Minimal additional computational complexity is introduced.

Abstract

Leveraging powerful deep learning techniques, the end-to-end (E2E) learning of communication system is able to outperform the classical communication system. Unfortunately, this communication system cannot be trained by deep learning without known channel. To deal with this problem, a generative adversarial network (GAN) based training scheme has been recently proposed to imitate the real channel. However, the gradient vanishing and overfitting problems of GAN will result in the serious performance degradation of E2E learning of communication system. To mitigate these two problems, we propose a residual aided GAN (RA-GAN) based training scheme in this paper. Particularly, inspired by the idea of residual learning, we propose a residual generator to mitigate the gradient vanishing problem by realizing a more robust gradient backpropagation. Moreover, to cope with the overfitting problem, we reconstruct the loss function for training by adding a regularizer, which limits the representation ability of RA-GAN. Simulation results show that the trained residual generator has better generation performance than the conventional generator, and the proposed RA-GAN based training scheme can achieve the near-optimal block error rate (BLER) performance with a negligible computational complexity increase in both the theoretical channel model and the ray-tracing based channel dataset.