LDPC codes, as an error correcting code close to the Shannon limit, are widely used in modern communication systems such as 5 G, satellite communication, deep space communication, and other fields. Traditional LDPC decoding algorithms, such as belief propagation (BP) algorithm and its variants, have achieved good performance, but face challenges such as high complexity and slow convergence, especially when dealing with long code lengths and high noise scenarios. The rise of deep learning has brought new opportunities for LDPC decoding, and its powerful features learning and pattern recognition capabilities are expected to break through the bottleneck of traditional decoding. Based on the overview of deep neural network decoding methods for LDPC codes by data-driven and model driven approaches, this paper analysis and comparison of error rate performance of short code $\mathbf{H} (8,16)$ matrix by convolutional neural networks (CNN), residual network (ResNet), and Kolmogorov-Arnold Network (KAN).LDPC codes, as an error correcting code close to the Shannon limit, are widely used in modern communication systems such as 5 G, satellite communication, deep space communication, and other fields. Traditional LDPC decoding algorithms, such as belief propagation (BP) algorithm and its variants, have achieved good performance, but face challenges such as high complexity and slow convergence, especially when dealing with long code lengths and high noise scenarios. The rise of deep learning has brought new opportunities for LDPC decoding, and its powerful features learning and pattern recognition capabilities are expected to break through the bottleneck of traditional decoding. Based on the overview of deep neural network decoding methods for LDPC codes by data-driven and model driven approaches, this paper analysis and comparison of error rate performance of short code$\mathbf{H} (8,16)$matrix by convolutional neural networks (CNN), residual network (ResNet), and Kolmogorov-Arnold Network (KAN).

IEEE International Conference on Artificial Intelligence, Computer Science and Information Processing (AICSIP)Jul 25, 20250 citations

Greedy Belief Propagation Algorithm for Low-Complexity LDPC Decoding

Yimo Zhen, Jinhui Chen, Zhan Zhang Xu +1 more

Lecture notes in networks and systemsJan 1, 20250 citations

A Model-Driven Quasi-ResNet Belief Propagation Neural Network Decoder for LDPC Codes

Liangsi Ma, Bei Liu, Xin Su +1 more

For the Belief Propagation (BP) algorithm of low-density parity-check (LDPC) codes, existing deep learning methods have a limited performance improvement and it is difficult to train deep-level networks. In this paper, a model-driven quasi-residual network (Quasi-ResNet) BP decoding architecture is proposed for LDPC codes to further improve the performance of standard BP decoding. This method feeds the reliable messages calculated in current iteration into the next iteration based on the shortcut connection, and adjusts the weight of shortcut connection based on the error Back Propagation algorithm of neural network to determine the optimal genetic proportion of reliable messages. The decoding architecture is composed of a model-driven deep neural network (DNN) and shortcut connection. Simulation results show that the decoder can not only unfold more layers quickly compared with the DNN-based BP decoder, but also further improve the decoding performance.For the Belief Propagation (BP) algorithm of low-density parity-check (LDPC) codes, existing deep learning methods have a limited performance improvement and it is difficult to train deep-level networks. In this paper, a model-driven quasi-residual network (Quasi-ResNet) BP decoding architecture is proposed for LDPC codes to further improve the performance of standard BP decoding. This method feeds the reliable messages calculated in current iteration into the next iteration based on the shortcut connection, and adjusts the weight of shortcut connection based on the error Back Propagation algorithm of neural network to determine the optimal genetic proportion of reliable messages. The decoding architecture is composed of a model-driven deep neural network (DNN) and shortcut connection. Simulation results show that the decoder can not only unfold more layers quickly compared with the DNN-based BP decoder, but also further improve the decoding performance.

IEEE Symposium on Computers and Communications (ISCC)Jul 9, 20231 citation

Low Complexity Deep Learning Method for Base Graph of Protograph LDPC Decoding

Shuo Peng Liang, Xingcheng Liu, Lin Zhang

Deep learning-based decoding algorithms have emerged as a focal point currently in contemporary research. Neural Offset Min-Sum Belief Propagation decoding algorithm is one of the traditional deep learning methods rooted in model-driven approaches. However, with the gradual increase in codeword length, there is an inevitable surge in the training cost and time complexity of such kind of deep learning algorithms. Addressing this issue, a novel deep learning algorithm based on the structural characteristics of the base graph in protograph LDPC codes is proposed. By strategically training the base graph and introducing a unique bit decoding allocation strategy, we endeavor to harmonize the Deep Learning algorithm with the intrinsic structure of the base graph itself. This approach contrasts favorably with several existing methods that utilize conventional segmental deep learning decoding algorithms for protograph LDPC codes. Simulation results demonstrate that, compared to other model-driven based deep learning algorithms, the proposed algorithm significantly reduces the number of parameters required for storage and training, while the loss in decoding performance remains within acceptable bounds.Deep learning-based decoding algorithms have emerged as a focal point currently in contemporary research. Neural Offset Min-Sum Belief Propagation decoding algorithm is one of the traditional deep learning methods rooted in model-driven approaches. However, with the gradual increase in codeword length, there is an inevitable surge in the training cost and time complexity of such kind of deep learning algorithms. Addressing this issue, a novel deep learning algorithm based on the structural characteristics of the base graph in protograph LDPC codes is proposed. By strategically training the base graph and introducing a unique bit decoding allocation strategy, we endeavor to harmonize the Deep Learning algorithm with the intrinsic structure of the base graph itself. This approach contrasts favorably with several existing methods that utilize conventional segmental deep learning decoding algorithms for protograph LDPC codes. Simulation results demonstrate that, compared to other model-driven based deep learning algorithms, the proposed algorithm significantly reduces the number of parameters required for storage and training, while the loss in decoding performance remains within acceptable bounds.

IEEE International Conference on Computer and Communications (ICCC)Dec 8, 20230 citations

Near optimum universal belief propagation based decoding of LDPC codes

J. Chen

IEEE Transactions on CommunicationsJan 1, 200219 citations

\mathbf{H} (8,16)

matrix by convolutional neural networks (CNN), residual network (ResNet), and Kolmogorov-Arnold Network (KAN).