Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

International Symposium on Information Theory and its Applications

Improving Convergence Speed of Neural Polar Decoder using Weighted Loss Function

Yiwei Lu, Shan Lu, Takaya Yamazato, Yeong-Luh Ueng

Published Nov 10, 2024• 0 citations
Publisher

Abstract

In recent years, neural network decoding of polar codes, such as neural belief propagation (BP), has been intro-duced. These methods use deep learning to transform the factor graph into a neural network model by unfolding the decoding iterations, thereby enhancing the accuracy of traditional decoding processes. However, current prevalent methodologies for loss function calculation only take into account the output of the final layer. In our analysis, we found that when calculating the loss function using only the output from the last layer, the convergence speed of the decoder significantly decreases, especially when the number of unfolded iterations is higher. In this paper, we incorporate the output of all iterations into the loss function in the original neural BP structure. Additionally, we optimize the loss function by assigning different weights to losses at different iterations. As a result, the weighted loss function not only provides a lower Bit Error Rate (BER) compared to the original neural BP decoder at lower SNR, but also accelerates convergence speed.

DOI
10.23919/isita60732.2024.10858209

Related papers

Learning to Decode Polar Codes With One-Bit Quantizer

Jian Shu Gao, Kai Niu, Chao Dong

A deep learning method for improving the performance of polar belief propagation (BP) decoder equipped with a one-bit quantizer is proposed. The method generalizes the standard polar BP algorithm by assigning weights to the layers of the unfolded factor graph. These weights can be learned autonomously using deep learning techniques. We prove that the improved polar BP decoder has a symmetric structure, so that the weights can be trained by an all-zero codeword rather than an exponential number of codewords. In order to accelerate the training convergence, a layer-based weight assignment scheme is designed, which decreases the amount of trainable weights. Simulation results show that the improved polar BP decoder with a one-bit quantizer outperforms the standard polar BP decoder with a 2-bit quantizer and achieves faster convergence.

IEEE Access•Jan 1, 2020•10 citations

Improved polar decoder based on deep learning

Weihong Xu, Zhizhen Wu, Yeong-Luh Ueng +2 more

Deep learning recently shows strong competitiveness to improve polar code decoding. However, suffering from prohibitive training and computation complexity, the conventional deep neural network (DNN) is only possible for very short code length. In this paper, the main problems of deep learning in decoding are well solved. We first present the multiple scaled belief propagation (BP) algorithm, aiming at obtaining faster convergence and better performance. Based on this, deep neural network decoder (NND) with low complexity and latency, is proposed for any code length. The training only requires a small set of zero codewords. Besides, its computation complexity is close to the original BP. Experiment results show that the proposed (64,32) NND with 5 iterations achieves even lower bit error rate (BER) than the 30-iteration conventional BP and (512, 256) NND also outperforms conventional BP decoder with same iterations. The hardware architecture of basic computation block is given and folding technique is also considered, saving about 50% hardware cost.

SiPS ... design and implementation - IEEE Workshop on Signal Processing Systems•Oct 1, 2017•157 citations

Improved Recurrent Neural Network based BP Decoding Algorithm for Polar Codes

Xue-lu DENG, Da-qin PENG

In recent years, the emerging Deep Learning (DL) technology has made progress in the field of decoding. Current polar code neural network decoder has faster convergence speed and better Bit Error Rate (BER) performance than Belief Propagation (BP) decoding. However, it still has the problem of high computational complexity. Therefore, in order to improve this problem, this paper adopts the idea of improving information update in the iterative process, and proposes a Recurrent Neural Network (RNN) Offset Min-Sum (OMS) BP decoding algorithm that improves Left information update (RNN-OMSBP-L) . The simulation results show that, compared with the Deep Neural Network (DNN) BP(DNN-BP) decoding algorithm, this algorithm replaces all multiplications with a cost of 6.25% addition. Compared with the current optimized RNN OMS and approximate BP(RNN-OMS-BP) decoding algorithm, the decoding algorithm in this paper uses improved information to reduce 25% of the addition operations with almost no loss in BER performance, while saving part of the storage space overhead. Under the same BER performance, it reduces the number of iterations by 37.5%.

•Aug 1, 2022•0 citations

A Low Complexity Neural Network-Based BP Decoder for Polar Codes

Yinyou Mao, Shizhan Cheng, Xingcheng Liu +1 more

In recent years, neural network-based BP decoders for polar codes have draw much attention, due to their faster convergence and better error-correction performance compared with conventional BP decoders. However, the prior neural BP decoders have high storage cost and training complexity due to massive number of training weights, and the performance improvement is slight. In this work, we first propose a 2D-MSMS algorithm with a shared weight scheme, in which the nodes in the same layer share a weight among different iterations. These learnable weights are optimized by deep learning techniques. Then, we propose a CRC-Aided relaxed 2D-MSMS polar de-coder by introducing relaxation method and CRC-Aided early termination scheme. Simulation results show that our proposed decoder can effectively improve BER performance at medium to high SNR and reduce the amount of training weights by more than 95%.

IEEE International Conference on Computer and Communications (ICCC)•Dec 9, 2022•1 citation

ResNet-Like Belief-Propagation Decoding for Polar Codes

Jian Shu Gao, Dexin Zhang, Jincheng Dai +2 more

The polar neural decoder has a performance improvement at the cost of additional storage and computation. In this letter, we first propose a ResNet-like BP architecture to improve the standard polar BP decoding. Each iteration inherits a portion of information from the previous iteration as additional input and passes its output to the next iteration. Second, trainable damping factors, which can be learned through deep learning techniques, are applied to determine the inheritance ratio in the ResNet-like BP. We allocate the damping factors flexibly and demonstrate the optimization of a shared constant damping factor provides the same level of performance with the individual optimization of the damping factor at each state. Moreover, we qualitatively explain the performance gain by analyzing the mutual information between the input and output of the decoder. Numerical and simulation results indicate that the ResNet-like BP decoder can effectively improve the error correction performance and accelerate convergence compared with the standard polar BP algorithm.

IEEE Wireless Communications Letters•Jan 13, 2021•17 citations

A BP-NN Decoding Algorithm for Polar Codes

Chen Wen, Jian Xiong, Lin Gui +1 more

Polar code is selected for the 5-th generation of wireless communication standard. Meanwhile, with the demand of low latency in 5G and great success in deep learning area, neural network decoder (NND) becomes a promising candidate for future decoder. However, NND is currently only feasible for very short code lengths. In this paper, we proposed a belief propagation-neural network (BP-NN) algorithm for polar codes based on partitioning. The core of our algorithm is replacing subblock of belief propagation (BP) decoder with NNDs, and using BP decoding framework to connect them. In addition, we also introduce a weight function to complete the message propagation process. Simulation results show the proposed algorithm reduces the decoding delay compared to the traditional BP algorithm and have a well bit error rate (BER) performance. At the same time, it also suitable for long polar codes.

International Conference on Wireless Communications and Signal Processing (WCSP)•Oct 1, 2019•4 citations
In recent years, neural network decoding of polar codes, such as neural belief propagation (BP), has been intro-duced. These methods use deep learning to transform the factor graph into a neural network model by unfolding the decoding iterations, thereby enhancing the accuracy of traditional decoding processes. However, current prevalent methodologies for loss function calculation only take into account the output of the final layer. In our analysis, we found that when calculating the loss function using only the output from the last layer, the convergence speed of the decoder significantly decreases, especially when the number of unfolded iterations is higher. In this paper, we incorporate the output of all iterations into the loss function in the original neural BP structure. Additionally, we optimize the loss function by assigning different weights to losses at different iterations. As a result, the weighted loss function not only provides a lower Bit Error Rate (BER) compared to the original neural BP decoder at lower SNR, but also accelerates convergence speed.
A deep learning method for improving the performance of polar belief propagation (BP) decoder equipped with a one-bit quantizer is proposed. The method generalizes the standard polar BP algorithm by assigning weights to the layers of the unfolded factor graph. These weights can be learned autonomously using deep learning techniques. We prove that the improved polar BP decoder has a symmetric structure, so that the weights can be trained by an all-zero codeword rather than an exponential number of codewords. In order to accelerate the training convergence, a layer-based weight assignment scheme is designed, which decreases the amount of trainable weights. Simulation results show that the improved polar BP decoder with a one-bit quantizer outperforms the standard polar BP decoder with a 2-bit quantizer and achieves faster convergence.
Deep learning recently shows strong competitiveness to improve polar code decoding. However, suffering from prohibitive training and computation complexity, the conventional deep neural network (DNN) is only possible for very short code length. In this paper, the main problems of deep learning in decoding are well solved. We first present the multiple scaled belief propagation (BP) algorithm, aiming at obtaining faster convergence and better performance. Based on this, deep neural network decoder (NND) with low complexity and latency, is proposed for any code length. The training only requires a small set of zero codewords. Besides, its computation complexity is close to the original BP. Experiment results show that the proposed (64,32) NND with 5 iterations achieves even lower bit error rate (BER) than the 30-iteration conventional BP and (512, 256) NND also outperforms conventional BP decoder with same iterations. The hardware architecture of basic computation block is given and folding technique is also considered, saving about 50% hardware cost.
In recent years, the emerging Deep Learning (DL) technology has made progress in the field of decoding. Current polar code neural network decoder has faster convergence speed and better Bit Error Rate (BER) performance than Belief Propagation (BP) decoding. However, it still has the problem of high computational complexity. Therefore, in order to improve this problem, this paper adopts the idea of improving information update in the iterative process, and proposes a Recurrent Neural Network (RNN) Offset Min-Sum (OMS) BP decoding algorithm that improves Left information update (RNN-OMSBP-L) . The simulation results show that, compared with the Deep Neural Network (DNN) BP(DNN-BP) decoding algorithm, this algorithm replaces all multiplications with a cost of 6.25% addition. Compared with the current optimized RNN OMS and approximate BP(RNN-OMS-BP) decoding algorithm, the decoding algorithm in this paper uses improved information to reduce 25% of the addition operations with almost no loss in BER performance, while saving part of the storage space overhead. Under the same BER performance, it reduces the number of iterations by 37.5%.
In recent years, neural network-based BP decoders for polar codes have draw much attention, due to their faster convergence and better error-correction performance compared with conventional BP decoders. However, the prior neural BP decoders have high storage cost and training complexity due to massive number of training weights, and the performance improvement is slight. In this work, we first propose a 2D-MSMS algorithm with a shared weight scheme, in which the nodes in the same layer share a weight among different iterations. These learnable weights are optimized by deep learning techniques. Then, we propose a CRC-Aided relaxed 2D-MSMS polar de-coder by introducing relaxation method and CRC-Aided early termination scheme. Simulation results show that our proposed decoder can effectively improve BER performance at medium to high SNR and reduce the amount of training weights by more than 95%.
The polar neural decoder has a performance improvement at the cost of additional storage and computation. In this letter, we first propose a ResNet-like BP architecture to improve the standard polar BP decoding. Each iteration inherits a portion of information from the previous iteration as additional input and passes its output to the next iteration. Second, trainable damping factors, which can be learned through deep learning techniques, are applied to determine the inheritance ratio in the ResNet-like BP. We allocate the damping factors flexibly and demonstrate the optimization of a shared constant damping factor provides the same level of performance with the individual optimization of the damping factor at each state. Moreover, we qualitatively explain the performance gain by analyzing the mutual information between the input and output of the decoder. Numerical and simulation results indicate that the ResNet-like BP decoder can effectively improve the error correction performance and accelerate convergence compared with the standard polar BP algorithm.
Polar code is selected for the 5-th generation of wireless communication standard. Meanwhile, with the demand of low latency in 5G and great success in deep learning area, neural network decoder (NND) becomes a promising candidate for future decoder. However, NND is currently only feasible for very short code lengths. In this paper, we proposed a belief propagation-neural network (BP-NN) algorithm for polar codes based on partitioning. The core of our algorithm is replacing subblock of belief propagation (BP) decoder with NNDs, and using BP decoding framework to connect them. In addition, we also introduce a weight function to complete the message propagation process. Simulation results show the proposed algorithm reduces the decoding delay compared to the traditional BP algorithm and have a well bit error rate (BER) performance. At the same time, it also suitable for long polar codes.