# Pruning Neural Belief Propagation Decoders

arXiv: https://arxiv.org/abs/2001.07464 · HTML: https://mlsanity.com/paper/2001.07464/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2020.

## Built on by (most cited first, 10 of 10)

- [KO codes: Inventing Nonlinear Encoding and Decoding for Reliable Wireless Communication via Deep-learning](https://mlsanity.com/paper/2108.12920/) (2021)
- [ProductAE: Towards Training Larger Channel Codes based on Neural Product Codes](https://mlsanity.com/paper/2110.04466/) (2021)
- [Cyclically Equivariant Neural Decoders for Cyclic Codes](https://mlsanity.com/paper/2105.05540/) (2021)
- [CRISP: Curriculum based Sequential Neural Decoders for Polar Code Family](https://mlsanity.com/paper/2210.00313/) (2022)
- [Neural Decoding with Optimization of Node Activations](https://mlsanity.com/paper/2206.00786/) (2022)
- [TinyTurbo: Efficient Turbo Decoders on Edge](https://mlsanity.com/paper/2209.15614/) (2022)
- [Improving the List Decoding Version of the Cyclically Equivariant Neural Decoder](https://mlsanity.com/paper/2106.07964/) (2021)
- [ProductAE: Toward Deep Learning Driven Error-Correction Codes of Large Dimensions](https://mlsanity.com/paper/2303.16424/) (2023)
- [Neural Network Decoders for Permutation Codes Correcting Different Errors](https://mlsanity.com/paper/2206.03315/) (2022)
- [A Scalable Graph Neural Network Decoder for Short Block Codes](https://mlsanity.com/paper/2211.06962/) (2022)

## Abstract (arXiv)

We consider near maximum-likelihood (ML) decoding of short linear block codes based on neural belief propagation (BP) decoding recently introduced by Nachmani et al.. While this method significantly outperforms conventional BP decoding, the underlying parity-check matrix may still limit the overall performance. In this paper, we introduce a method to tailor an overcomplete parity-check matrix to (neural) BP decoding using machine learning. We consider the weights in the Tanner graph as an indication of the importance of the connected check nodes (CNs) to decoding and use them to prune unimportant CNs. As the pruning is not tied over iterations, the final decoder uses a different parity-check matrix in each iteration. For Reed-Muller and short low-density parity-check codes, we achieve performance within 0.27 dB and 1.5 dB of the ML performance while reducing the complexity of the decoder.