Low-complexity Near-optimum Symbol Detection Based on Neural Enhancement of Factor Graphs

TL;DR

This paper introduces neural enhancement techniques for factor graph-based symbol detection in channels with inter-symbol interference, significantly improving performance while maintaining low complexity.

Contribution

It proposes neural belief propagation and dynamic factor graph transitions to mitigate cycle effects, approaching optimal detection performance.

Findings

Massive performance improvements demonstrated in simulations

Approaches approach maximum a posteriori detection

Complexity remains linear in block length and channel memory

Abstract

We consider the application of the factor graph framework for symbol detection on linear inter-symbol interference channels. Based on the Ungerboeck observation model, a detection algorithm with appealing complexity properties can be derived. However, since the underlying factor graph contains cycles, the sum-product algorithm (SPA) yields a suboptimal algorithm. In this paper, we develop and evaluate efficient strategies to improve the performance of the factor graph-based symbol detection by means of neural enhancement. In particular, we consider neural belief propagation and generalizations of the factor nodes as an effective way to mitigate the effect of cycles within the factor graph. By applying a generic preprocessor to the channel output, we propose a simple technique to vary the underlying factor graph in every SPA iteration. Using this dynamic factor graph transition, we intend to preserve the extrinsic nature of the SPA messages which is otherwise impaired due to cycles. Simulation results show that the proposed methods can massively improve the detection performance, even approaching the maximum a posteriori performance for various transmission scenarios, while preserving a complexity which is linear in both the block length and the channel memory.