Enhancing K-user Interference Alignment for Discrete Constellations via Learning

TL;DR

This paper introduces a deep learning method to optimize interference alignment in K-user channels with discrete constellations, significantly improving sum-rate performance over traditional linear schemes.

Contribution

It develops a neural network-based approach to learn constellation mappings that enhance interference alignment and sum-rate in discrete-input interference channels, extending beyond existing linear algorithms.

Findings

Neural network-learned constellations outperform baseline algorithms.

Enhanced alignment in beamforming and effective constellation at receivers.

Improved sum-rate performance demonstrated through numerical results.

Abstract

In this paper, we consider a K-user interference channel where interference among the users is neither too strong nor too weak, a scenario that is relatively underexplored in the literature. We propose a novel deep learning-based approach to design the encoder and decoder functions that aim to maximize the sumrate of the interference channel for discrete constellations. We first consider the MaxSINR algorithm, a state-of-the-art linear scheme for Gaussian inputs, as the baseline and then propose a modified version of the algorithm for discrete inputs. We then propose a neural network-based approach that learns a constellation mapping with the objective of maximizing the sumrate. We provide numerical results to show that the constellations learned by the neural network-based approach provide enhanced alignments, not just in beamforming directions but also in terms of the effective constellation at the receiver, thereby leading to improved sum-rate performance.