Decoding Short LDPC Codes via BP-RNN Diversity and Reliability-Based Post-Processing

Joachim Rosseel (1, 2) , Valérian Mannoni (1) , Inbar Fijalkow (2) , Valentin Savin (1)

1 Université Grenoble Alpes, CEA, Leti, F-38000, Grenoble, France
2 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes

This paper investigates decoder diversity architectures for short low-density parity-check (LDPC) codes, based on recurrent neural network (RNN) models of the belief-propagation (BP) algorithm. We propose a new approach to achieve decoder diversity in the waterfall region, by specializing BP-RNN decoders to specific classes of errors, with absorbing set support. We further combine our approach with an ordered statistics decoding (OSD) post-processing step, which effectively leverages the bit-error rate optimization deriving from the use of the binary cross-entropy loss function. We show that a single specialized BP-RNN decoder combines better than BP with the OSD postprocessing step. Moreover, combining OSD post-processing with the diversity brought by the use of multiple BP-RNN decoders, provides an efficient way to bridge the gap to maximum likelihood decoding.

Mots clés: LDPC; short LDPC; neural network aided decoding; belief propagation; ordered statistics decoding postprocessing

Domaines: Réseaux et télécommunications [cs.NI]; Réseau de neurones [cs.NE]

Joachim Rosseel, Valérian Mannoni, Inbar Fijalkow, Valentin Savin. Decoding Short LDPC Codes via BP-RNN Diversity and Reliability-Based Post-Processing. IEEE Transactions on Communications, 2022, pp.1-1. ⟨10.1109/TCOMM.2022.3218821⟩. ⟨hal-03845023⟩