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

TL;DR

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%, exhibits performance equivalent to state-of-the-art receivers with 2.5 times shorter running time, and adapts to various 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.

Figures (12)

• Figure 1: Block diagram of a MIMO system based on BICM studerSoftInputSoft2010. The MIMO turbo receiver iteratively exchanges soft information between the MIMO detector, which combines model-based algorithms with NNs, and the channel decoder.
• Figure 2: Visual representation of the EP-based turbo receiver at the $\iota$-th turbo iteration. The black solid lines indicate the EP iterations, while the blue dash lines indicate the interaction with the channel decoder (Dec).
• Figure 3: Visual representation of the proposed turbo receiver structure for GEPNet at the $\iota$-th turbo iteration. The black solid lines depict the unfolding structure of GEPNet, while the blue dash lines depict the interaction with the channel decoder (Dec).
• Figure 4: Message passing process of the GNN.
• Figure 5: Overview of the three-step training process for the EXT-GEPNet.

Theorems & Definitions (2)

• Remark 1
• Remark 2