DeepIC: Coding for Interference Channels via Deep Learning
This addresses the gap between theoretical and practical coding for wireless communication, offering a more efficient solution for multi-user interference scenarios.
The paper tackles the problem of designing practical codes for two-user interference channels, where existing schemes like Han-Kobayashi are too complex. It introduces DeepIC, a deep learning-based convolutional neural network code with an iterative decoder, which significantly outperforms time division and treating interference as noise for additive white Gaussian noise channels with moderate interference.
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.