DeepIC: Coding for Interference Channels via Deep Learning

TL;DR

This paper introduces DeepIC, a deep learning-based coding scheme for two-user interference channels, which outperforms traditional methods like TD and TIN in practical scenarios with moderate interference.

Contribution

The paper proposes DeepIC, a convolutional neural network-based coding scheme that effectively bridges the gap between theoretical interference management and practical implementation.

Findings

DeepIC outperforms TD and TIN schemes in moderate interference conditions.

DeepIC achieves significant performance gains over traditional coding schemes.

The approach demonstrates the potential of deep learning for practical interference channel coding.

Abstract

The two-user interference channel is a model for multi one-to-one communications, where two transmitters wish to communicate with their corresponding receivers via a shared wireless medium. Two most common and simple coding schemes are time division (TD) and treating interference as noise (TIN). Interestingly, it is shown that there exists an asymptotic scheme, called Han-Kobayashi scheme, that performs better than TD and TIN. However, Han-Kobayashi scheme has impractically high complexity and is designed for asymptotic settings, which leads to a gap between information theory and practice. In this paper, we focus on designing practical codes for interference channels. As it is challenging to analytically design practical codes with feasible complexity, we apply deep learning to learn codes for interference channels. We demonstrate that DeepIC, a convolutional neural network-based code with an iterative decoder, outperforms TD and TIN by a significant margin for two-user additive white Gaussian noise channels with moderate amount of interference.