Interference Cancellation GAN Framework for Dynamic Channels

TL;DR

This paper proposes an online GAN-based framework for interference cancellation in dynamic communication channels, enabling rapid adaptation and outperforming existing neural network models in highly variable environments.

Contribution

It introduces a novel online training framework combining deep unfolding and GANs to adapt interference cancellation models to changing channels efficiently.

Findings

Outperforms recent neural network models on dynamic channels

Surpasses static channel performance in experiments

Enables swift adaptation to channel changes

Abstract

Symbol detection is a fundamental and challenging problem in modern communication systems, e.g., multiuser multiple-input multiple-output (MIMO) setting. Iterative Soft Interference Cancellation (SIC) is a state-of-the-art method for this task and recently motivated data-driven neural network models, e.g. DeepSIC, that can deal with unknown non-linear channels. However, these neural network models require thorough timeconsuming training of the networks before applying, and is thus not readily suitable for highly dynamic channels in practice. We introduce an online training framework that can swiftly adapt to any changes in the channel. Our proposed framework unifies the recent deep unfolding approaches with the emerging generative adversarial networks (GANs) to capture any changes in the channel and quickly adjust the networks to maintain the top performance of the model. We demonstrate that our framework significantly outperforms recent neural network models on highly dynamic channels and even surpasses those on the static channel in our experiments.