GCEPNet: Graph Convolution-Enhanced Expectation Propagation for Massive MIMO Detection

TL;DR

GCEPNet introduces a novel graph convolution-enhanced expectation propagation method for massive MIMO detection, capturing variable correlations more effectively and achieving state-of-the-art performance with faster inference.

Contribution

This paper is the first to connect system models with graph convolution and design data-dependent coefficients for improved MIMO detection.

Findings

Achieves state-of-the-art MIMO detection performance.

Faster inference compared to existing methods.

Effectively captures variable correlations through graph convolution.

Abstract

Massive MIMO (multiple-input multiple-output) detection is an important topic in wireless communication and various machine learning based methods have been developed recently for this task. Expectation Propagation (EP) and its variants are widely used for MIMO detection and have achieved the best performance. However, EP-based solvers fail to capture the correlation between unknown variables, leading to a loss of information, and in addition, they are computationally expensive. In this paper, we show that the real-valued system can be modeled as spectral signal convolution on graph, through which the correlation between unknown variables can be captured. Based on such analysis, we propose graph convolution-enhanced expectation propagation (GCEPNet). GCEPNet incorporates data-dependent attention scores into Chebyshev polynomial for powerful graph convolution with better generalization capacity. It enables a better estimation of the cavity distribution for EP and empirically achieves the state-of-the-art (SOTA) MIMO detection performance with much faster inference speed. To our knowledge, we are the first to shed light on the connection between the system model and graph convolution, and the first to design the data-dependent coefficients for graph convolution.