© 2026 Aqora Quantum S.A.S.

Terms Privacy Legal Notice

IEEE Transactions on Cognitive Communications and Networking

A Neural Network-Based Compressive LDPC Decoder Design Over Correlated Noise Channel

Ying Li, Baoye Zhang, Bin Tan, Jun Hui Wu, Die Hu

Published Feb 9, 2024• 1 citation

Abstract

To combat the correlated noise and utilize the non-equiprobability of the source, we propose a novel Low-density parity-check (LDPC) decoder design based on a priori information and neural network, which includes two neural networks, namely Correlated-Denoising Convolutional Neural Network (Correlated-DnCNN) and Belief Propagation-Deep Neural Network (BP-DNN), respectively. Correlated-DnCNN is used to remove the correlation of channel noise and reduce the noise power. BP-DNN is used to eliminate the harmful effect of short cycles of the Tanner graph and explore the priori information of the source. With the priori information to assist in initializing the input nodes of the BP-DNN network, we introduce compression capability to the LDPC, thus the proposed scheme can improve efficiency significantly when there is a large amount of compressible data in the physical layer. To train the Correlated-DnCNN and BP-DNN jointly, we design a new three-objective joint denoising-decoding loss function, which can not only guarantee the decoding performance, but also constrain the noise to conform to the normal distribution as much as possible, and improve the network convergence performance. Experiments show that the proposed decoding framework can remove the noise correlation, reduce the noise power, and improve the decoding performance effectively.

DOI: 10.1109/tccn.2024.3364234

Related papers

A UnetNND-BP Architecture for Channel Decoding Under Correlated Noise

Huiying Chen, Pengchao Zhao, Chengju Li

In this letter, we introduce a Unet-based neural network denoiser-belief propagation (UnetNND-BP) architecture with two training modes to improve the decoding performance of low-density parity-check (LDPC) codes. In the supervised learning mode, UnetNND-BP achieves better performance than benchmark schemes, while in the self-supervised learning mode, it achieves comparable performance.

IEEE Communications Letters•Feb 5, 2024•0 citations

Learning to Decode LDPC Codes with Finite-Alphabet Message Passing

Bane V. Vasic, Xin Wei Xiao, Shu Lin

In this paper, we discuss the perspectives of utilizing deep neural networks (DNN) to decode Low-Density Parity Check (LDPC) codes. The main idea is to build a neural network to learn and optimize a conventional iterative decoder of LDPC codes. A DNN is based on Tanner graph, and the activation functions emulate message update functions in variable and check nodes. We impose a symmetry on weight matrices which makes it possible to train the DNN on a single codeword and noise realizations only. Based on the trained weights and the bias, we further quantize messages in such DNN-based decoder with 3-bit precision while maintaining no loss in error performance compared to the min-sum algorithm. We use examples to present that the DNN framework can be applied to various code lengths. The simulation results show that, the trained weights and bias make the iterative DNN decoder converge faster and thus achieve higher throughput at the cost of trivial additional decoding complexity.

Information Theory and Applications Workshop (ITA)•Feb 1, 2018•36 citations

A new LDPC decoding scheme based on BP and Gated Neural Network

Yong Liu, Xiaolin Liu, Zhongyi Ding +2 more

In long wave communication scenarios, channel interferences lead to noise correlation. Since traditional belief propagation (BP) decoding algorithm is designed based on additive white Gaussian noise (AWGN), a performance cost will appear when it comes to correlated noise. In this paper, a new LDPC decoding scheme that applies to correlated Gaussian noise is proposed. We design a BP-gated neural network-BP structure to carry on two rounds of BP decoding with the second round based on optimized noise. By adopting gated neurons in typical NN, CNN, training performance is improved. Simulation shows that compared with BP decoding algorithm, the new decoding scheme outperforms traditional method by 0.5~0.61 dB when bit error rate is 10-6. This decoding scheme also works on pectinate noise with performance gain of 1.5 dB.

International Conference on Information Science, Computer Technology and Transportation (ISCTT)•Nov 1, 2020•5 citations

Modified Iterative BP-CNN Decoder Under Correlated Noise with Symmetric α-stable Distributions

Senlin Li, Sihui Zheng, Jingwen Zhang +2 more

Recently, an iterative belief propagation-convolutional neural network (BP-CNN) decoder has been proposed to process the low-density parity-check (LDPC) decoding under correlated noise. However, in many practical scenarios, correlated noise may have extra special characteristics, such as impulse. Therefore, when used in such scenarios, there will be some space for the performance improvement of the BP-CNN decoder, since its loss functions cannot make full use of the special characteristics of correlated noise. Fortunately, the impulsive property of correlated noise can be effectively described by the symmetric α-stable (SαS) distribution model. Thus, we propose a novel loss function to train a well-behaved CNN model under correlated noise with SαS distributions. In order to take advantage of the features of SαS distributions captured by CNN, the proposed loss function involves a probability density function (PDF) estimation of the residual noise and a similarity detection. The similarity detection uses the Kullback-Leibler (KL) divergence method to compare the similarity between the estimated PDF and the Gaussian distribution. In the BP-CNN decoder, the residual noise is defined as the difference between the actual noise and the estimated noise. The effectiveness of our modifications for the BP-CNN decoder will be demonstrated with simulation results.

IEEE International Conference on Signal, Information and Data Processing (ICSIDP)•Dec 1, 2019•0 citations

Normalized Neural Network for Belief Propagation LDPC Decoding

Yiduo Tang, Lin Zhou, Shuying Zhang +2 more

BP decoding algorithm is one of the commonly used decoding algorithms for LDPC codes. To adapt LDPC codes to different 5G scenarios and further improve the decoding performance of short LDPC codes, a scheme combining model-driven deep learning with a traditional BP decoding algorithm is proposed. With the advantages of model-driven, this solution expands the decoding iteration process between the check node and the variable node into a neural network and proposes a parameter normalization optimization solution to solve the problem of the program with many training parameters, the edge weights of the optimized Tanner graph are re-assigned and bound. Simulation results show that the proposed scheme can improve the decoding performance of LDPC codes with short lengths.

IEEE International Conference on Networking, Sensing and Control (ICNSC)•Dec 3, 2021•8 citations

Intelligent LDPC Decoding Using Graph Neural Networks for Beyond 5G Communication Systems

Ambar Bajpai

With changing scenarios in Beyond 5G (B5G) systems, channel coding methods will be faced with stronger requirements for reliability, flexibility, and low latency.Conventional decoding algorithms such as Belief Propagation (BP) are efficient in structured contexts but not sufficiently flexible to respond effectively to dynamic and noisy channel conditions.In this study, we introduces a new Graph Neural Network (GNN)-based solution to decode Low-Density Parity-Check (LDPC) codes by taking advantage of the intrinsic bipartite graph representation of Tanner graphs.The proposed decoder learns a data-driven messagepassing algorithm that performs better than BP over a large range of signal-to-noise ratios (SNRs) and block lengths.The experimental results show that the GNN-based decoder yields much lower bit error rates (BER), faster convergence, and better resistance to noise variability than belief propagation, especially at medium to high SNR levels.Thus, our findings highlight the foundation for scalable, adaptive, and intelligent decoding systems in B5G and 6G architectures.

Journal of information and communication convergence engineering•Dec 31, 2025•0 citations

To combat the correlated noise and utilize the non-equiprobability of the source, we propose a novel Low-density parity-check (LDPC) decoder design based on a priori information and neural network, which includes two neural networks, namely Correlated-Denoising Convolutional Neural Network (Correlated-DnCNN) and Belief Propagation-Deep Neural Network (BP-DNN), respectively. Correlated-DnCNN is used to remove the correlation of channel noise and reduce the noise power. BP-DNN is used to eliminate the harmful effect of short cycles of the Tanner graph and explore the priori information of the source. With the priori information to assist in initializing the input nodes of the BP-DNN network, we introduce compression capability to the LDPC, thus the proposed scheme can improve efficiency significantly when there is a large amount of compressible data in the physical layer. To train the Correlated-DnCNN and BP-DNN jointly, we design a new three-objective joint denoising-decoding loss function, which can not only guarantee the decoding performance, but also constrain the noise to conform to the normal distribution as much as possible, and improve the network convergence performance. Experiments show that the proposed decoding framework can remove the noise correlation, reduce the noise power, and improve the decoding performance effectively.

In this paper, we discuss the perspectives of utilizing deep neural networks (DNN) to decode Low-Density Parity Check (LDPC) codes. The main idea is to build a neural network to learn and optimize a conventional iterative decoder of LDPC codes. A DNN is based on Tanner graph, and the activation functions emulate message update functions in variable and check nodes. We impose a symmetry on weight matrices which makes it possible to train the DNN on a single codeword and noise realizations only. Based on the trained weights and the bias, we further quantize messages in such DNN-based decoder with 3-bit precision while maintaining no loss in error performance compared to the min-sum algorithm. We use examples to present that the DNN framework can be applied to various code lengths. The simulation results show that, the trained weights and bias make the iterative DNN decoder converge faster and thus achieve higher throughput at the cost of trivial additional decoding complexity.

In long wave communication scenarios, channel interferences lead to noise correlation. Since traditional belief propagation (BP) decoding algorithm is designed based on additive white Gaussian noise (AWGN), a performance cost will appear when it comes to correlated noise. In this paper, a new LDPC decoding scheme that applies to correlated Gaussian noise is proposed. We design a BP-gated neural network-BP structure to carry on two rounds of BP decoding with the second round based on optimized noise. By adopting gated neurons in typical NN, CNN, training performance is improved. Simulation shows that compared with BP decoding algorithm, the new decoding scheme outperforms traditional method by 0.5~0.61 dB when bit error rate is 10-6. This decoding scheme also works on pectinate noise with performance gain of 1.5 dB.

Recently, an iterative belief propagation-convolutional neural network (BP-CNN) decoder has been proposed to process the low-density parity-check (LDPC) decoding under correlated noise. However, in many practical scenarios, correlated noise may have extra special characteristics, such as impulse. Therefore, when used in such scenarios, there will be some space for the performance improvement of the BP-CNN decoder, since its loss functions cannot make full use of the special characteristics of correlated noise. Fortunately, the impulsive property of correlated noise can be effectively described by the symmetric α-stable (SαS) distribution model. Thus, we propose a novel loss function to train a well-behaved CNN model under correlated noise with SαS distributions. In order to take advantage of the features of SαS distributions captured by CNN, the proposed loss function involves a probability density function (PDF) estimation of the residual noise and a similarity detection. The similarity detection uses the Kullback-Leibler (KL) divergence method to compare the similarity between the estimated PDF and the Gaussian distribution. In the BP-CNN decoder, the residual noise is defined as the difference between the actual noise and the estimated noise. The effectiveness of our modifications for the BP-CNN decoder will be demonstrated with simulation results.

BP decoding algorithm is one of the commonly used decoding algorithms for LDPC codes. To adapt LDPC codes to different 5G scenarios and further improve the decoding performance of short LDPC codes, a scheme combining model-driven deep learning with a traditional BP decoding algorithm is proposed. With the advantages of model-driven, this solution expands the decoding iteration process between the check node and the variable node into a neural network and proposes a parameter normalization optimization solution to solve the problem of the program with many training parameters, the edge weights of the optimized Tanner graph are re-assigned and bound. Simulation results show that the proposed scheme can improve the decoding performance of LDPC codes with short lengths.

With changing scenarios in Beyond 5G (B5G) systems, channel coding methods will be faced with stronger requirements for reliability, flexibility, and low latency.Conventional decoding algorithms such as Belief Propagation (BP) are efficient in structured contexts but not sufficiently flexible to respond effectively to dynamic and noisy channel conditions.In this study, we introduces a new Graph Neural Network (GNN)-based solution to decode Low-Density Parity-Check (LDPC) codes by taking advantage of the intrinsic bipartite graph representation of Tanner graphs.The proposed decoder learns a data-driven messagepassing algorithm that performs better than BP over a large range of signal-to-noise ratios (SNRs) and block lengths.The experimental results show that the GNN-based decoder yields much lower bit error rates (BER), faster convergence, and better resistance to noise variability than belief propagation, especially at medium to high SNR levels.Thus, our findings highlight the foundation for scalable, adaptive, and intelligent decoding systems in B5G and 6G architectures.