We introduce a two-stage decimation process to improve the performance of neural belief propagation (NBP), recently introduced by Nachmani et al., for short low-density parity-check (LDPC) codes. In the first stage, we build a list by iterating between a conventional NBP decoder and guessing the least reliable bit. The second stage iterates between a conventional NBP decoder and learned decimation, where we use a neural network to decide the decimation value for each bit. For a (128,64) LDPC code, the proposed NBP with decimation outperforms NBP decoding by 0.75 dB and performs within 1 dB from maximum-likelihood decoding at a block error rate of 10−4.
@article{arxiv.2011.02161,
title = {Learned Decimation for Neural Belief Propagation Decoders},
author = {Andreas Buchberger and Christian Häger and Henry D. Pfister and Laurent Schmalen and Alexandre Graell i Amat},
journal= {arXiv preprint arXiv:2011.02161},
year = {2020}
}