Sparse graph neural network aided efficient decoder for polar codes under bursty interference

In this paper, a sparse graph neural network-aided (SGNN-aided) decoder is proposed for improving the decoding performance of polar codes under bursty interference. Firstly, a sparse factor graph is constructed using the encoding characteristic to achieve high-throughput polar decoding. To further i...

Full description

Saved in:
Bibliographic Details
Main Authors: Shengyu Zhang, Zhongxiu Feng, Zhe Peng, Lixia Xiao, Tao Jiang
Format: Article
Language:English
Published: KeAi Communications Co., Ltd. 2025-04-01
Series:Digital Communications and Networks
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352864823001773
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849729529347571712
author Shengyu Zhang
Zhongxiu Feng
Zhe Peng
Lixia Xiao
Tao Jiang
author_facet Shengyu Zhang
Zhongxiu Feng
Zhe Peng
Lixia Xiao
Tao Jiang
author_sort Shengyu Zhang
collection DOAJ
description In this paper, a sparse graph neural network-aided (SGNN-aided) decoder is proposed for improving the decoding performance of polar codes under bursty interference. Firstly, a sparse factor graph is constructed using the encoding characteristic to achieve high-throughput polar decoding. To further improve the decoding performance, a residual gated bipartite graph neural network is designed for updating embedding vectors of heterogeneous nodes based on a bidirectional message passing neural network. This framework exploits gated recurrent units and residual blocks to address the gradient disappearance in deep graph recurrent neural networks. Finally, predictions are generated by feeding the embedding vectors into a readout module. Simulation results show that the proposed decoder is more robust than the existing ones in the presence of bursty interference and exhibits high universality.
format Article
id doaj-art-2050700322704f62b29d21d2c14f3b5e
institution DOAJ
issn 2352-8648
language English
publishDate 2025-04-01
publisher KeAi Communications Co., Ltd.
record_format Article
series Digital Communications and Networks
spelling doaj-art-2050700322704f62b29d21d2c14f3b5e2025-08-20T03:09:12ZengKeAi Communications Co., Ltd.Digital Communications and Networks2352-86482025-04-0111235936410.1016/j.dcan.2023.12.002Sparse graph neural network aided efficient decoder for polar codes under bursty interferenceShengyu Zhang0Zhongxiu Feng1Zhe Peng2Lixia Xiao3Tao Jiang4Research Center of 6G Mobile Communications, School of Cyber Science and Engineering, and Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, 430074, ChinaResearch Center of 6G Mobile Communications, School of Cyber Science and Engineering, and Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan, 430074, ChinaResearch Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, ChinaResearch Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, ChinaResearch Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan, 430074, China; Corresponding author.In this paper, a sparse graph neural network-aided (SGNN-aided) decoder is proposed for improving the decoding performance of polar codes under bursty interference. Firstly, a sparse factor graph is constructed using the encoding characteristic to achieve high-throughput polar decoding. To further improve the decoding performance, a residual gated bipartite graph neural network is designed for updating embedding vectors of heterogeneous nodes based on a bidirectional message passing neural network. This framework exploits gated recurrent units and residual blocks to address the gradient disappearance in deep graph recurrent neural networks. Finally, predictions are generated by feeding the embedding vectors into a readout module. Simulation results show that the proposed decoder is more robust than the existing ones in the presence of bursty interference and exhibits high universality.http://www.sciencedirect.com/science/article/pii/S2352864823001773Sparse graph neural networkPolar codesBursty interferenceSparse factor graphMessage passing neural network
spellingShingle Shengyu Zhang
Zhongxiu Feng
Zhe Peng
Lixia Xiao
Tao Jiang
Sparse graph neural network aided efficient decoder for polar codes under bursty interference
Digital Communications and Networks
Sparse graph neural network
Polar codes
Bursty interference
Sparse factor graph
Message passing neural network
title Sparse graph neural network aided efficient decoder for polar codes under bursty interference
title_full Sparse graph neural network aided efficient decoder for polar codes under bursty interference
title_fullStr Sparse graph neural network aided efficient decoder for polar codes under bursty interference
title_full_unstemmed Sparse graph neural network aided efficient decoder for polar codes under bursty interference
title_short Sparse graph neural network aided efficient decoder for polar codes under bursty interference
title_sort sparse graph neural network aided efficient decoder for polar codes under bursty interference
topic Sparse graph neural network
Polar codes
Bursty interference
Sparse factor graph
Message passing neural network
url http://www.sciencedirect.com/science/article/pii/S2352864823001773
work_keys_str_mv AT shengyuzhang sparsegraphneuralnetworkaidedefficientdecoderforpolarcodesunderburstyinterference
AT zhongxiufeng sparsegraphneuralnetworkaidedefficientdecoderforpolarcodesunderburstyinterference
AT zhepeng sparsegraphneuralnetworkaidedefficientdecoderforpolarcodesunderburstyinterference
AT lixiaxiao sparsegraphneuralnetworkaidedefficientdecoderforpolarcodesunderburstyinterference
AT taojiang sparsegraphneuralnetworkaidedefficientdecoderforpolarcodesunderburstyinterference