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

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, this paper proposes a residual aided GAN (RA-GAN) based training scheme. 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 back propagation. 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 conventional generator, and the proposed RA-GAN based training scheme can achieve the near-optimal block error rate (BLER) performance.