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

IEEE International Conference on Acoustics Speech and Signal Processing

Adaptive Reweighted Sparse Belief Propagation Decoding for Polar Codes

Robert M. Oliveira, Rodrigo C. de Lamare

Published Mar 18, 2024• 0 citations
Publisher

Abstract

In this paper, we present an adaptive reweighted sparse belief propagation (AR-SBP) decoder for polar codes. The AR-SBP technique is inspired by decoders that employ the sum-product algorithm for low-density parity-check codes. In particular, the AR-SBP decoding strategy introduces reweighting of the exchanged log-likelihood-ratio in order to refine the message passing, improving the performance of the decoder and reducing the number of required iterations. An analysis of the convergence of AR-SBP is carried out along with a study of the complexity of the analyzed decoders. Numerical examples show that the AR-SBP decoder outperforms existing decoding algorithms for a reduced number of iterations, enabling low-latency applications.

DOI
10.1109/icassp48485.2024.10446017

Related papers

Study of Adaptive Reweighted Sparse Belief Propagation Decoders for Polar Codes

Robert M. Oliveira, Rodrigo C. de Lamare

In this paper, we present an adaptive reweighted sparse belief propagation (AR-SBP) decoder for polar codes. The AR-SBP technique is inspired by decoders that employ the sum-product algorithm for low-density parity-check codes. In particular, the AR-SBP decoding strategy introduces reweighting of the exchanged log-likelihood-ratio in order to refine the message passing, improving the performance of the decoder and reducing the number of required iterations. An analysis of the convergence of AR-SBP is carried out along with a study of the complexity of the analyzed decoders. Numerical examples show that the AR-SBP decoder outperforms existing decoding algorithms for a reduced number of iterations, enabling low-latency applications.

arXiv:2404.04674•Apr 6, 2024•0 citations

Sparse Graphs for Belief Propagation Decoding of Polar Codes

Sebastian Cammerer, Moustafa Ebada, Ahmed Elkelesh +1 more

We describe a novel approach to interpret a polar code as a low-density parity-check (LDPC)-like code with an underlying sparse decoding graph. This sparse graph is based on the encoding factor graph of polar codes and is suitable for conventional belief propagation (BP) decoding. We discuss several pruning techniques based on the check node decoder (CND) and variable node decoder (VND) update equations, significantly reducing the size (i.e., decoding complexity) of the parity-check matrix. As a result, iterative polar decoding can then be conducted on a sparse graph, akin to the traditional well-established LDPC decoding, e.g., using a fully parallel sum-product algorithm (SPA). This facilitates the systematic analysis and design of polar codes using the well-established tools known from analyzing LDPC codes. We show that the proposed iterative polar decoder has a negligible performance loss for short-to-intermediate codelengths compared to Arikan's original BP decoder. Finally, the proposed decoder is shown to benefit from both reduced complexity and reduced memory requirements and, thus, is more suitable for hardware implementations.

arXiv:1712.08538•IEEE International Symposium on Information Theory (ISIT)•Jun 1, 2018•58 citations

Adaptive Reweighted Freezing Belief Propagation Decoding for Polar Codes

Xiaojin Guo, ZHANG Jingtao

To address the challenges of high computational redundancy, slow convergence speed, and limited decoding performance in Belief Propagation (BP) decoding of polar codes, this paper proposes an Adaptive Reweighted Freezing (ARF) BP decoding algorithm. This algorithm introduces an adaptive reweighting mechanism to regulate the weights of message updates, thereby accelerating the convergence of the decoding process. Furthermore, it implements a freezing judgment strategy for converged nodes within the factor graph to eliminate redundant calculations. Simulation results demonstrate that, in the low Signal-to-Noise Ratio (SNR) region, the ARF-BP algorithm achieves a performance gain of approximately 1.1 dB compared to the traditional BP decoding algorithm. Moreover, compared to BP decoding with the G-matrix early stopping criterion, it reduces the average number of iterations by about 64% and effectively freezes approximately 20% of the factor graph nodes. Featuring low latency and low power consumption, this algorithm is well-suited for critical scenarios such as 5G massive Machine Type Communications and Ultra-Reliable Low-Latency Communications.

•Jan 1, 2026•0 citations

A hybrid belief propagation decoding algorithms of LDPC codes for fast convergence

Tso-Cho Chen, Chia‐Jung Li, Erl‐Huei Lu

A hybrid belief propagation (BP) decoding algorithm for low-density parity-check code is proposed to accelerate the convergence of decoding and reduce the number of decoding iterations. The hybrid scheme is presented by integrating the BP algorithm with the bit-flipping function which is used as adaptive weighted factor in the BP iteration decoding. The adaptive weighting factor is based on the average weighted reliability measure of the hard output of decoder. The proposed hybrid adaptive weighted iteration scheme can efficiently increase the convergence speed of the belief propagation decoding and therefore improve the error performance. Simulation results show that the proposed algorithm can significantly reduce the decoding complexity and achieve better error performances as compared with the sum-product algorithm.

Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC)•Jul 1, 2013•5 citations

Polar Decoding on Sparse Graphs with Deep Learning

Weihong Xu, Xiaohu You, Chuan Zhang +1 more

In this paper, we present a sparse neural network decoder (SNND) of polar codes based on belief propagation (BP) and deep learning. At first, the conventional factor graph of polar BP decoding is converted to the bipartite Tanner graph similar to low-density parity-check (LDPC) codes. Then the Tanner graph is unfolded and translated into the graphical representation of deep neural network (DNN). The complex sum-product algorithm (SPA) is modified to min-sum (MS) approximation with low complexity. We dramatically reduce the number of weight by using single weight to parameterize the networks. Optimized by the training techniques of deep learning, proposed SNND achieves comparative decoding performance of SPA and obtains about 0.5 dB gain over MS decoding on (128,64) and (256,128) codes. Moreover, 60% complexity reduction is achieved and the decoding latency is significantly lower than the conventional polar BP.

arXiv:1811.09801•Asilomar Conference on Signals, Systems and Computers (ACSSC)•Oct 1, 2018•36 citations

A simplified belief propagation decoder for polar codes

Yingxian Zhang, Qingshuang Zhang, Xiaofei Pan +2 more

In this paper, we propose a simplified belief propagation(SBP) decoder for the polar codes, where the update calculation for the messages of the so-called frozen nodes is replaced by setting these nodes' messages by prior probabilities during the BP procedure. Numerical results show that the derived SBP yields almost the same performance as the BP decoders in the literature, while the computational complexity is reduced significantly, which make our SBP more suitable for practical application as compared to the existing BP decoders.

IEEE International Wireless Symposium•Mar 1, 2014•26 citations
In this paper, we present an adaptive reweighted sparse belief propagation (AR-SBP) decoder for polar codes. The AR-SBP technique is inspired by decoders that employ the sum-product algorithm for low-density parity-check codes. In particular, the AR-SBP decoding strategy introduces reweighting of the exchanged log-likelihood-ratio in order to refine the message passing, improving the performance of the decoder and reducing the number of required iterations. An analysis of the convergence of AR-SBP is carried out along with a study of the complexity of the analyzed decoders. Numerical examples show that the AR-SBP decoder outperforms existing decoding algorithms for a reduced number of iterations, enabling low-latency applications.
In this paper, we present an adaptive reweighted sparse belief propagation (AR-SBP) decoder for polar codes. The AR-SBP technique is inspired by decoders that employ the sum-product algorithm for low-density parity-check codes. In particular, the AR-SBP decoding strategy introduces reweighting of the exchanged log-likelihood-ratio in order to refine the message passing, improving the performance of the decoder and reducing the number of required iterations. An analysis of the convergence of AR-SBP is carried out along with a study of the complexity of the analyzed decoders. Numerical examples show that the AR-SBP decoder outperforms existing decoding algorithms for a reduced number of iterations, enabling low-latency applications.
We describe a novel approach to interpret a polar code as a low-density parity-check (LDPC)-like code with an underlying sparse decoding graph. This sparse graph is based on the encoding factor graph of polar codes and is suitable for conventional belief propagation (BP) decoding. We discuss several pruning techniques based on the check node decoder (CND) and variable node decoder (VND) update equations, significantly reducing the size (i.e., decoding complexity) of the parity-check matrix. As a result, iterative polar decoding can then be conducted on a sparse graph, akin to the traditional well-established LDPC decoding, e.g., using a fully parallel sum-product algorithm (SPA). This facilitates the systematic analysis and design of polar codes using the well-established tools known from analyzing LDPC codes. We show that the proposed iterative polar decoder has a negligible performance loss for short-to-intermediate codelengths compared to Arikan's original BP decoder. Finally, the proposed decoder is shown to benefit from both reduced complexity and reduced memory requirements and, thus, is more suitable for hardware implementations.
To address the challenges of high computational redundancy, slow convergence speed, and limited decoding performance in Belief Propagation (BP) decoding of polar codes, this paper proposes an Adaptive Reweighted Freezing (ARF) BP decoding algorithm. This algorithm introduces an adaptive reweighting mechanism to regulate the weights of message updates, thereby accelerating the convergence of the decoding process. Furthermore, it implements a freezing judgment strategy for converged nodes within the factor graph to eliminate redundant calculations. Simulation results demonstrate that, in the low Signal-to-Noise Ratio (SNR) region, the ARF-BP algorithm achieves a performance gain of approximately 1.1 dB compared to the traditional BP decoding algorithm. Moreover, compared to BP decoding with the G-matrix early stopping criterion, it reduces the average number of iterations by about 64% and effectively freezes approximately 20% of the factor graph nodes. Featuring low latency and low power consumption, this algorithm is well-suited for critical scenarios such as 5G massive Machine Type Communications and Ultra-Reliable Low-Latency Communications.
A hybrid belief propagation (BP) decoding algorithm for low-density parity-check code is proposed to accelerate the convergence of decoding and reduce the number of decoding iterations. The hybrid scheme is presented by integrating the BP algorithm with the bit-flipping function which is used as adaptive weighted factor in the BP iteration decoding. The adaptive weighting factor is based on the average weighted reliability measure of the hard output of decoder. The proposed hybrid adaptive weighted iteration scheme can efficiently increase the convergence speed of the belief propagation decoding and therefore improve the error performance. Simulation results show that the proposed algorithm can significantly reduce the decoding complexity and achieve better error performances as compared with the sum-product algorithm.
In this paper, we present a sparse neural network decoder (SNND) of polar codes based on belief propagation (BP) and deep learning. At first, the conventional factor graph of polar BP decoding is converted to the bipartite Tanner graph similar to low-density parity-check (LDPC) codes. Then the Tanner graph is unfolded and translated into the graphical representation of deep neural network (DNN). The complex sum-product algorithm (SPA) is modified to min-sum (MS) approximation with low complexity. We dramatically reduce the number of weight by using single weight to parameterize the networks. Optimized by the training techniques of deep learning, proposed SNND achieves comparative decoding performance of SPA and obtains about 0.5 dB gain over MS decoding on (128,64) and (256,128) codes. Moreover, 60% complexity reduction is achieved and the decoding latency is significantly lower than the conventional polar BP.
In this paper, we propose a simplified belief propagation(SBP) decoder for the polar codes, where the update calculation for the messages of the so-called frozen nodes is replaced by setting these nodes' messages by prior probabilities during the BP procedure. Numerical results show that the derived SBP yields almost the same performance as the BP decoders in the literature, while the computational complexity is reduced significantly, which make our SBP more suitable for practical application as compared to the existing BP decoders.