Graph Neural Network-Enhanced Expectation Propagation Algorithm for MIMO Turbo Receivers

TL;DR

This paper introduces a novel GNN-enhanced expectation propagation algorithm for MIMO turbo receivers, improving detection accuracy and reducing computational complexity through edge pruning and specialized training.

Contribution

It presents a new GNN-based EP detector with a training procedure for extrinsic information and an edge pruning strategy to enhance efficiency and performance.

Findings

Outperforms EP turbo approaches by over 1 dB at BER of 10^{-5}

Achieves similar performance to state-of-the-art with 2.5x less running time

Adapts effectively to various MIMO scenarios

Abstract

Deep neural networks (NNs) are considered a powerful tool for balancing the performance and complexity of multiple-input multiple-output (MIMO) receivers due to their accurate feature extraction, high parallelism, and excellent inference ability. Graph NNs (GNNs) have recently demonstrated outstanding capability in learning enhanced message passing rules and have shown success in overcoming the drawback of inaccurate Gaussian approximation of expectation propagation (EP)-based MIMO detectors. However, the application of the GNN-enhanced EP detector to MIMO turbo receivers is underexplored and non-trivial due to the requirement of extrinsic information for iterative processing. This paper proposes a GNN-enhanced EP algorithm for MIMO turbo receivers, which realizes the turbo principle of generating extrinsic information from the MIMO detector through a specially designed training procedure. Additionally, an edge pruning strategy is designed to eliminate redundant connections in the original fully connected model of the GNN utilizing the correlation information inherently from the EP algorithm. Edge pruning reduces the computational cost dramatically and enables the network to focus more attention on the weights that are vital for performance. Simulation results and complexity analysis indicate that the proposed MIMO turbo receiver outperforms the EP turbo approaches by over 1 dB at the bit error rate of $10^{-5}$, exhibits performance equivalent to state-of-the-art receivers with 2.5 times shorter running time, and adapts to various scenarios.