Semi-supervised MIMO Detection Using Cycle-consistent Generative Adversarial Network

In this paper, a new semi-supervised deep MIMO detection approach using a cycle-consistent generative adversarial network (cycleGAN) is proposed, which performs the detection without any prior knowledge of underlying channel models. Specifically, we propose the cycleGAN detector by constructing a bidirectional loop of least squares generative adversarial networks (LS-GAN). The forward direction of the loop learns to model the transmission process, while the backward direction learns to detect the transmitted signals. By optimizing the cycle-consistency of the transmitted and received signals through this loop, the proposed method is able to train a specific detector block-by-block to fit the operating channel. The training is conducted online, including a supervised phase using pilots and an unsupervised phase using received payload data. This semi-supervised training strategy weakens the demand for the scale of labelled training dataset, which is related to the number of pilots, and thus the overhead is effectively reduced. Numerical results show that the proposed semi-blind cycleGAN detector achieves better bit error-rate (BER) than existing semi-blind deep learning detection methods as well as conditional linear detectors, especially when nonlinear distortion of the power amplifiers at the transmitter is considered.