# Graph Neural Networks for Channel Decoding

arXiv: https://arxiv.org/abs/2207.14742 · HTML: https://mlsanity.com/paper/2207.14742/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 34 references that are in the map.
- First posted on arXiv 29 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [An Introduction to Deep Learning for the Physical Layer](https://mlsanity.com/paper/1702.00832/) (2017)
- [Sionna: An Open-Source Library for Next-Generation Physical Layer Research](https://mlsanity.com/paper/2203.11854/) (2022)
- [Learning to Decode Linear Codes Using Deep Learning](https://mlsanity.com/paper/1607.04793/) (2016)
- [Neural Enhanced Belief Propagation on Factor Graphs](https://mlsanity.com/paper/2003.01998/) (2020)
- [DeepRx: Fully Convolutional Deep Learning Receiver](https://mlsanity.com/paper/2005.01494/) (2020)
- [Error Correction Code Transformer](https://mlsanity.com/paper/2203.14966/) (2022)
- [Deep Learning for Decoding of Linear Codes - A Syndrome-Based Approach](https://mlsanity.com/paper/1802.04741/) (2018)
- [Trainable Communication Systems: Concepts and Prototype](https://mlsanity.com/paper/1911.13055/) (2019)
- [Low-complexity Near-optimum Symbol Detection Based on Neural Enhancement of Factor Graphs](https://mlsanity.com/paper/2203.16417/) (2022)
- [Scalable Polar Code Construction for Successive Cancellation List Decoding: A Graph Neural Network-Based Approach](https://mlsanity.com/paper/2207.01105/) (2022)

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

- [Boosting Learning for LDPC Codes to Improve the Error-Floor Performance](https://mlsanity.com/paper/2310.07194/) (2023)
- [Learning Linear Block Error Correction Codes](https://mlsanity.com/paper/2405.04050/) (2024)
- [Decoding Quantum LDPC Codes Using Graph Neural Networks](https://mlsanity.com/paper/2408.05170/) (2024)
- [Accelerating and Compressing Deep Neural Networks for Massive MIMO CSI Feedback](https://mlsanity.com/paper/2304.01914/) (2023)
- [Data-driven Energy Efficiency Modelling in Large-scale Networks: An Expert Knowledge and ML-based Approach](https://mlsanity.com/paper/2401.00443/) (2023)
- [DUIDD: Deep-Unfolded Interleaved Detection and Decoding for MIMO Wireless Systems](https://mlsanity.com/paper/2212.07816/) (2022)
- [Optimizing Serially Concatenated Neural Codes with Classical Decoders](https://mlsanity.com/paper/2212.10355/) (2022)
- [5G LDPC Linear Transformer for Channel Decoding](https://mlsanity.com/paper/2501.14102/) (2025)
- [Trapped by simplicity: When Transformers fail to learn from noisy features](https://mlsanity.com/paper/2602.08695/) (2026)
- [Scalable Mamba-Based Message-Passing Neural Decoder for Error-Correcting Codes](https://mlsanity.com/paper/2605.10681/) (2026)

## Abstract (arXiv)

In this work, we propose a fully differentiable graph neural network (GNN)-based architecture for channel decoding and showcase a competitive decoding performance for various coding schemes, such as low-density parity-check (LDPC) and BCH codes. The idea is to let a neural network (NN) learn a generalized message passing algorithm over a given graph that represents the forward error correction (FEC) code structure by replacing node and edge message updates with trainable functions. Contrary to many other deep learning-based decoding approaches, the proposed solution enjoys scalability to arbitrary block lengths and the training is not limited by the curse of dimensionality. We benchmark our proposed decoder against state-of-the-art in conventional channel decoding as well as against recent deep learning-based results. For the (63,45) BCH code, our solution outperforms weighted belief propagation (BP) decoding by approximately 0.4 dB with significantly less decoding iterations and even for 5G NR LDPC codes, we observe a competitive performance when compared to conventional BP decoding. For the BCH codes, the resulting GNN decoder can be fully parametrized with only 9640 weights.