Graph Neural Network-based Joint Equalization and Decoding

TL;DR

This paper introduces a graph neural network-based method for joint equalization and decoding in communication systems, demonstrating improved error correction and reduced latency compared to traditional techniques.

Contribution

It presents a novel GNN architecture for joint equalization and decoding that is robust to cycles and enables end-to-end learning, with a parallel flooding schedule for latency reduction.

Findings

GNN-based JED outperforms traditional methods by 2.25 dB in BER at low latency.

The proposed approach is robust against cycles in factor graphs.

Parallel flooding schedule reduces latency and improves error correction.

Abstract

This paper proposes to use graph neural networks (GNNs) for equalization, that can also be used to perform joint equalization and decoding (JED). For equalization, the GNN is build upon the factor graph representations of the channel, while for JED, the factor graph is expanded by the Tanner graph of the parity-check matrix (PCM) of the channel code, sharing the variable nodes (VNs). A particularly advantageous property of the GNN is the robustness against cycles in the factor graphs which is the main problem for belief propagation (BP)-based equalization. As a result of having a fully deep learning-based receiver, joint optimization instead of individual optimization of the components is enabled, so-called end-to-end learning. Furthermore, we propose a parallel flooding schedule that further reduces the latency, which turns out to improve also the error correcting performance. The proposed approach is analyzed and compared to state-of-the-art baselines in terms of error correcting capability and latency. At a fixed low latency, the flooding GNN for JED demonstrates a gain of 2.25 dB in bit error rate (BER) compared to an iterative Bahl--Cock--Jelinek--Raviv (BCJR)-BP baseline.