LDPC Decoding With Degree-Specific Neural Message Weights and RCQ Decoding

Linfang Wang

doi:10.1109/TCOMM.2023.3343387

LDPC Decoding With Degree-Specific Neural Message Weights and RCQ Decoding

2024-04-01

2

OA

AI

DOI：10.1109/TCOMM.2023.3343387

Original

Original request for help

Save

Abstract

En 中文

Recently, neural networks have improved MinSum message-passing decoders for low-density parity-check (LDPC) codes by multiplying or adding weights to the messages, where the weights are determined by a neural network. The neural network complexity to determine distinct weights for each edge is high, often limiting the application to relatively short LDPC codes. Furthermore, storing separate weights for every edge and every iteration can be a burden for hardware implementations. To reduce neural network complexity and storage requirements, this paper proposes a family of weight-sharing schemes that use the same weight for edges that have the same check node degree and/or variable node degree. Our simulation results show that node-degree-based weight-sharing can deliver the same performance requiring distinct weights for each node. This paper also combines these degree-specific neural weights with a reconstruction-computation-quantization (RCQ) decoder to produce a weighted RCQ (W-RCQ) decoder. The W-RCQ decoder with node-degree-based weight sharing has a reduced hardware requirement compared with the original RCQ decoder. As an additional contribution, this paper identifies and resolves a gradient explosion issue that can arise when training neural LDPC decoders.

Keywords:

Decoding

Training

Neurons

Hardware

Simulation

Biological neural networks

Iterative decoding

LDPC decoder

neural decoder

low-bitwidth decoding

hardware efficiency

layered decoding

FPGA

LDPC Decoding With Degree-Specific Neural Message Weights and RCQ Decoding

Abstract

Journal

Organization