Neural Enhancement of Factor Graph-based Symbol Detection

TL;DR

This paper explores neural enhancement techniques to improve cyclic factor graph-based symbol detection in channels with inter-symbol interference, combining neural belief propagation and optimized preprocessing for better accuracy and efficiency.

Contribution

It introduces neural belief propagation and a linear preprocessing method to enhance cyclic factor graph-based symbol detection performance.

Findings

Neural belief propagation improves detection accuracy.

Preprocessing reduces complexity and enhances performance.

Modified observation model significantly benefits detection.

Abstract

We study the application of the factor graph framework for symbol detection on linear inter-symbol interference channels. Cyclic factor graphs have the potential to yield low-complexity symbol detectors, but are suboptimal if the ubiquitous sum-product algorithm is applied. In this paper, we present and evaluate strategies to improve the performance of cyclic factor graph-based symbol detection algorithms by means of neural enhancement. In particular, we apply neural belief propagation as an effective way to counteract the effect of cycles within the factor graph. We further propose the application and optimization of a linear preprocessor of the channel output. By modifying the observation model, the preprocessing can effectively change the underlying factor graph, thereby significantly improving the detection performance as well as reducing the complexity.