Rate Compatible LDPC Neural Decoding Network: A Multi-Task Learning Approach

TL;DR

This paper introduces a multi-task learning neural network for LDPC decoding that efficiently handles multiple code rates within a single model, improving adaptability across various channel conditions.

Contribution

It presents a rate-compatible LDPC neural decoding network leveraging multi-task learning and raptor-like code structures, enabling simultaneous decoding at multiple rates without performance loss.

Findings

Effective multi-rate decoding demonstrated in experiments

Parameter sharing reduces model complexity

Maintains frame error rate across code rates

Abstract

Deep learning based decoding networks have shown significant improvement in decoding LDPC codes, but the neural decoders are limited by rate-matching operations such as puncturing or extending, thus needing to train multiple decoders with different code rates for a variety of channel conditions. In this correspondence, we propose a Multi-Task Learning based rate-compatible LDPC ecoding network, which utilizes the structure of raptor-like LDPC codes and can deal with multiple code rates. In the proposed network, different portions of parameters are activated to deal with distinct code rates, which leads to parameter sharing among tasks. Numerical experiments demonstrate the effectiveness of the proposed method. Training the specially designed network under multiple code rates makes the decoder compatible with multiple code rates without sacrificing frame error rate performance.