# A recipe of training neural network-based LDPC decoders

arXiv: https://arxiv.org/abs/2205.00481 · HTML: https://mlsanity.com/paper/2205.00481/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 35 references that are in the map.
- First posted on arXiv 1 May 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Survey of Deep Learning Techniques for Autonomous Driving](https://mlsanity.com/paper/1910.07738/) (2019)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [Deep Learning for Medical Image Processing: Overview, Challenges and Future](https://mlsanity.com/paper/1704.06825/) (2017)
- [Deep Learning Methods for Improved Decoding of Linear Codes](https://mlsanity.com/paper/1706.07043/) (2017)
- [Learning to Decode Linear Codes Using Deep Learning](https://mlsanity.com/paper/1607.04793/) (2016)
- [Pelee: A Real-Time Object Detection System on Mobile Devices](https://mlsanity.com/paper/1804.06882/) (2018)
- [Neural Offset Min-Sum Decoding](https://mlsanity.com/paper/1701.05931/) (2017)
- [When Face Recognition Meets with Deep Learning: an Evaluation of Convolutional Neural Networks for Face Recognition](https://mlsanity.com/paper/1504.02351/) (2015)
- [An Iterative BP-CNN Architecture for Channel Decoding](https://mlsanity.com/paper/1707.05697/) (2017)
- [Learned Belief-Propagation Decoding with Simple Scaling and SNR Adaptation](https://mlsanity.com/paper/1901.08621/) (2019)
- [RNN Decoding of Linear Block Codes](https://mlsanity.com/paper/1702.07560/) (2017)
- [Learning from the Syndrome](https://mlsanity.com/paper/1810.10902/) (2018)
- [ADMM-based Decoder for Binary Linear Codes Aided by Deep Learning](https://mlsanity.com/paper/2002.07601/) (2020)
- [Neural-Network-Optimized Degree-Specific Weights for LDPC MinSum Decoding](https://mlsanity.com/paper/2107.04221/) (2021)

## Abstract (arXiv)

It is known belief propagation decoding variants of LDPC codes can be unrolled easily as neural networks after assigning differed weights to message passing edges flexibly. In this paper we focus on how to determine these weights, in the form of trainable paramters, within a framework of deep learning. Firstly, a new method is proposed to generate high-quality training data via exploiting an approximation to the targeted mixture density. Then the strong positive correlation between training loss and decoding metrics is fully exposed after tracing the training evolution curves. Lastly, for the purpose of facilitating training convergence and reducing decoding complexity, we highlight the necessity of slashing the number of trainable parameters while emphasizing the locations of these survived ones, which is justified in the extensive simulation.