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

arXiv:2412.15897 · International ITG Conference on Systems, Communications and Coding (SCC)

Spiking Neural Belief Propagation Decoder for LDPC Codes with Small Variable Node Degrees

Alexander von Bank, Eike-Manuel Edelmann, Jonathan Mandelbaum, Laurent Schmalen

Published Mar 10, 2025• 0 citations
arXivHTMLPDF

Abstract

Spiking neural networks (SNNs) promise energyefficient data processing by imitating the event-based behavior of biological neurons. In previous work, we introduced the enlarge-likelihood-each-notable-amplitude spiking-neural-network (ELENA-SNN) decoder, a novel decoding algorithm for low-density parity-check (LDPC) codes. The decoder integrates SNNs into belief propagation (BP) decoding by approximating the check node (CN) update equation using SNNs. However, when decoding LDPC codes with a small variable node (VN) degree, the approximation gets too rough, and the ELENASNN decoder does not yield good results. This paper introduces the multi-level ELENA-SNN (ML-ELENA-SNN) decoder, which is an extension of the ELENA-SNN decoder. Instead of a single SNN approximating the CN update, multiple SNNs are applied in parallel, resulting in a higher resolution and higher dynamic range of the exchanged messages. We show that the ML-ELENASNN decoder performs similarly to the ubiquitous normalized min-sum decoder for the$(38400,30720)$regular LDPC code with a VN degree of$d_{v}=3$and a CN degree of$d_{\mathrm{c}}=15$.

DOI
10.1109/ieeeconf62907.2025.10949115

Related papers

Spiking Neural Belief Propagation Decoder for Short Block Length LDPC Codes

Alexander von Bank, Eike-Manuel Edelmann, Sisi Miao +2 more

Spiking neural networks (SNNs) are neural networks that enable energy-efficient signal processing due to their event-based nature. This letter proposes a novel decoding algorithm for low-density parity-check (LDPC) codes that integrates SNNs into belief propagation (BP) decoding by approximating the check node update equations using SNNs. For the (273,191) and (1023,781) finite-geometry LDPC code, the proposed decoder outperforms sum-product decoder at high signal-to-noise ratios (SNRs). The decoder achieves a similar bit error rate to normalized sum-product decoding with successive relaxation. Furthermore, the novel decoding operates without requiring knowledge of the SNR, making it robust to SNR mismatch.

arXiv:2410.11543•IEEE Communications Letters•Nov 6, 2024•5 citations

A Neuromorphic Approach to LDPC Decoding with Spiking Belief Propagation

Lucas Pelz, Ahsan Javed Awan, Mustafa Özger

The rapid growth of mobile data traffic demands increasingly energy-efficient error correction solutions. Traditional decoding based on Belief Propagation (BP) often relies on the approximate Min-Sum (MS) algorithm for efficiency reasons, leading to performance degradation. While machine learning approaches like Neural Normalized Offset Min-Sum (NNOMS) mitigate this, they also introduce complexity inherent to artificial neural networks (ANNs). To address this trade-off, this paper designs and evaluates a Spiking Normalized Offset Min-Sum (SNOMS), a Spiking Neural Network-based decoder compatible with Digital Neuromorphic Hardware (DNH) such as Intel's Loihi 2. SNOMS translates the parameter-learned decoding of NNOMS into the event-driven domain. Through simulation, SNOMS achieves performance competitive with its NNOMS baseline, incurring a maximum penalty of only 0.05 dB on Low-Density Parity-Check (LDPC) codes when measuring Block Error Rate. These results points us toward both more efficient trainable decoding algorithms and specialized, energyefficient neuromorphic decoding hardware, building a foundation for future sustainable wireless communication.

Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit)•Jun 2, 2026•0 citations

Pruning and Quantizing Neural Belief Propagation Decoders

Andreas Buchberger, Christian Häger, Henry D. Pfister +2 more

We consider near maximum-likelihood (ML) decoding of short linear block codes. In particular, we propose a novel decoding approach based on neural belief propagation (NBP) decoding recently introduced by Nachmani et al. in which we allow a different parity-check matrix in each iteration of the algorithm. The key idea is to consider NBP decoding over an overcomplete parity-check matrix and use the weights of NBP as a measure of the importance of the check nodes (CNs) to decoding. The unimportant CNs are then pruned. In contrast to NBP, which performs decoding on a given fixed parity-check matrix, the proposed pruning-based neural belief propagation (PB-NBP) typically results in a different parity-check matrix in each iteration. For a given complexity in terms of CN evaluations, we show that PB-NBP yields significant performance improvements with respect to NBP. We apply the proposed decoder to the decoding of a Reed-Muller code, a short low-density parity-check (LDPC) code, and a polar code. PB-NBP outperforms NBP decoding over an overcomplete parity-check matrix by 0.27-0.31 dB while reducing the number of required CN evaluations by up to 97%. For the LDPC code, PB-NBP outperforms conventional belief propagation with the same number of CN evaluations by 0.52 dB. We further extend the pruning concept to offset min-sum decoding and introduce a pruning-based neural offset min-sum (PB-NOMS) decoder, for which we jointly optimize the offsets and the quantization of the messages and offsets. We demonstrate performance 0.5 dB from ML decoding with 5-bit quantization for the Reed-Muller code.

arXiv:2011.13594•IEEE Journal on Selected Areas in Communications•Dec 4, 2020•52 citations

Low Complexity Neural Network-Aided NMS LDPC Decoder

Honghao Shi, Mingyang Zhong, Zhiyong Luo +1 more

For recent years, deep learning has been studied and utilized among decoders in wireless and optical communication. For low density parity check (LDPC) codes, most works use neural network (NN) to implement the belief propagation (BP) decoder and unfold its iterations into layers activated by different functions. However, the whole decoder composed by neural network performs lots of non-linear operations, which are time consuming and unfriendly to hardware implementation. In this work, a neural network-aided normalized min-sum (NN-aided NMS) decoder for LDPC code is proposed, in which the normalization factors are inferred from input log likelihood ratio (LLR) by apre-trained NN, while maintaining check and variable nodes processing the same as in min-sum (MS) decoder. In order to test the proposed decoder with irregular LDPC code, a rate-7/8 one was constructed using progressive edge growth (PEG) algorithm, showing better error correction capability than the standard of consultative committee for space data systems (CCSDS) LDPC (8176,7154) code by 0.08 dB with the same rate. Simulation results show that, NN-aided NMS decoder outperforms MS decoder by 0.3 dB, and its performance approaches BP decoder with a gap of 0.02 dB, which is 50% closer than the best NMS decoder using 0.7 as the normalization factor. The proposed decoder has good performance for both regular and irregular LDPC codes, and needs much less computation complexity than BP decoder. It introduces more linear computation than NMS decoder but achieves better bit error rate (BER) performance, thus becoming a good complement between BP and NMS decoder when trading off among complexity, error correction performance and hardware implementation for wireless and satellite communication.

Computing, Communications and IoT Applications (ComComAp)•Nov 26, 2021•8 citations

Generalized Two-Magnitude Check Node Updating with Self Correction for 5G LDPC Codes Decoding

Wei Zhou, Michael Lentmaier

The min-sum (MS) and approximate-min* (a-min*) algorithms are alternatives of the belief propagation (BP) algorithm for decoding low-density parity-check (LDPC) codes. To lower the BP decoding complexity, both algorithms compute two magnitudes at each check node (CN) and pass them to the neighboring variable nodes (VNs).In this work we propose a new algorithm, ga-min*, that generalizes the MS and a-min* in terms of number of incoming messages to a CN.We analyze and demonstrate a condition to improve the performance when applying self-correction to the ga-min*. Simulations on 5G LDPC codes show that the proposed decoding algorithm yields comparable performance to the a-min* with a significant reduction in complexity, and it is robust against LLR mismatch.

Systems Communications•Jan 1, 2019•7 citations

An optimized min-sum variable node layering for LDPC decoding

Nassib Laouini, Larbi Ben Hadj Slama, Ammar Bouallègue

Layered decoding is well appreciated in Low-Density Parity-Check (LDPC) decoder implementation since it provides efficient and high-throughput implementation of LDPC decoders. Variable-Node Layered Belief Propagation (VL-BP) algorithm and their reduced-complexity derivatives for LDPC codes are presented. The VL-BP algorithm is a modification of Belief Propagation algorithm (BP), where the variable nodes are divided in subgroups called layers and each iteration is broken into multiple sub-iterations. Some simplifications can also be made to lower the complexity of both BP and CL-BP algorithms, and particularly the complexity of the check node update rule. In this paper, we consider Variable Node Layered BP (VL-BP) algorithm and propose an optimized min-sum VL-BP (MS VL-BP) algorithm for decoding LDPC code which has better performance not only from MS VL-BP algorithm but also from BP algorithm. In this decoding method, unlike other layered algorithms, we consider for the first layer a set of variable nodes that has a low value of the intrinsic information. Simulation results show that good performance can be achieved, and which can even be improved by the addition of either a normalization term or an additive offset term.

•Apr 1, 2014•1 citation
Spiking neural networks (SNNs) promise energyefficient data processing by imitating the event-based behavior of biological neurons. In previous work, we introduced the enlarge-likelihood-each-notable-amplitude spiking-neural-network (ELENA-SNN) decoder, a novel decoding algorithm for low-density parity-check (LDPC) codes. The decoder integrates SNNs into belief propagation (BP) decoding by approximating the check node (CN) update equation using SNNs. However, when decoding LDPC codes with a small variable node (VN) degree, the approximation gets too rough, and the ELENASNN decoder does not yield good results. This paper introduces the multi-level ELENA-SNN (ML-ELENA-SNN) decoder, which is an extension of the ELENA-SNN decoder. Instead of a single SNN approximating the CN update, multiple SNNs are applied in parallel, resulting in a higher resolution and higher dynamic range of the exchanged messages. We show that the ML-ELENASNN decoder performs similarly to the ubiquitous normalized min-sum decoder for the(38400,30720)(38400,30720)(38400,30720)regular LDPC code with a VN degree ofdv=3d_{v}=3dv​=3and a CN degree ofdc=15d_{\mathrm{c}}=15dc​=15.
Spiking neural networks (SNNs) are neural networks that enable energy-efficient signal processing due to their event-based nature. This letter proposes a novel decoding algorithm for low-density parity-check (LDPC) codes that integrates SNNs into belief propagation (BP) decoding by approximating the check node update equations using SNNs. For the (273,191) and (1023,781) finite-geometry LDPC code, the proposed decoder outperforms sum-product decoder at high signal-to-noise ratios (SNRs). The decoder achieves a similar bit error rate to normalized sum-product decoding with successive relaxation. Furthermore, the novel decoding operates without requiring knowledge of the SNR, making it robust to SNR mismatch.
The rapid growth of mobile data traffic demands increasingly energy-efficient error correction solutions. Traditional decoding based on Belief Propagation (BP) often relies on the approximate Min-Sum (MS) algorithm for efficiency reasons, leading to performance degradation. While machine learning approaches like Neural Normalized Offset Min-Sum (NNOMS) mitigate this, they also introduce complexity inherent to artificial neural networks (ANNs). To address this trade-off, this paper designs and evaluates a Spiking Normalized Offset Min-Sum (SNOMS), a Spiking Neural Network-based decoder compatible with Digital Neuromorphic Hardware (DNH) such as Intel's Loihi 2. SNOMS translates the parameter-learned decoding of NNOMS into the event-driven domain. Through simulation, SNOMS achieves performance competitive with its NNOMS baseline, incurring a maximum penalty of only 0.05 dB on Low-Density Parity-Check (LDPC) codes when measuring Block Error Rate. These results points us toward both more efficient trainable decoding algorithms and specialized, energyefficient neuromorphic decoding hardware, building a foundation for future sustainable wireless communication.
We consider near maximum-likelihood (ML) decoding of short linear block codes. In particular, we propose a novel decoding approach based on neural belief propagation (NBP) decoding recently introduced by Nachmani et al. in which we allow a different parity-check matrix in each iteration of the algorithm. The key idea is to consider NBP decoding over an overcomplete parity-check matrix and use the weights of NBP as a measure of the importance of the check nodes (CNs) to decoding. The unimportant CNs are then pruned. In contrast to NBP, which performs decoding on a given fixed parity-check matrix, the proposed pruning-based neural belief propagation (PB-NBP) typically results in a different parity-check matrix in each iteration. For a given complexity in terms of CN evaluations, we show that PB-NBP yields significant performance improvements with respect to NBP. We apply the proposed decoder to the decoding of a Reed-Muller code, a short low-density parity-check (LDPC) code, and a polar code. PB-NBP outperforms NBP decoding over an overcomplete parity-check matrix by 0.27-0.31 dB while reducing the number of required CN evaluations by up to 97%. For the LDPC code, PB-NBP outperforms conventional belief propagation with the same number of CN evaluations by 0.52 dB. We further extend the pruning concept to offset min-sum decoding and introduce a pruning-based neural offset min-sum (PB-NOMS) decoder, for which we jointly optimize the offsets and the quantization of the messages and offsets. We demonstrate performance 0.5 dB from ML decoding with 5-bit quantization for the Reed-Muller code.
For recent years, deep learning has been studied and utilized among decoders in wireless and optical communication. For low density parity check (LDPC) codes, most works use neural network (NN) to implement the belief propagation (BP) decoder and unfold its iterations into layers activated by different functions. However, the whole decoder composed by neural network performs lots of non-linear operations, which are time consuming and unfriendly to hardware implementation. In this work, a neural network-aided normalized min-sum (NN-aided NMS) decoder for LDPC code is proposed, in which the normalization factors are inferred from input log likelihood ratio (LLR) by apre-trained NN, while maintaining check and variable nodes processing the same as in min-sum (MS) decoder. In order to test the proposed decoder with irregular LDPC code, a rate-7/8 one was constructed using progressive edge growth (PEG) algorithm, showing better error correction capability than the standard of consultative committee for space data systems (CCSDS) LDPC (8176,7154) code by 0.08 dB with the same rate. Simulation results show that, NN-aided NMS decoder outperforms MS decoder by 0.3 dB, and its performance approaches BP decoder with a gap of 0.02 dB, which is 50% closer than the best NMS decoder using 0.7 as the normalization factor. The proposed decoder has good performance for both regular and irregular LDPC codes, and needs much less computation complexity than BP decoder. It introduces more linear computation than NMS decoder but achieves better bit error rate (BER) performance, thus becoming a good complement between BP and NMS decoder when trading off among complexity, error correction performance and hardware implementation for wireless and satellite communication.
The min-sum (MS) and approximate-min* (a-min*) algorithms are alternatives of the belief propagation (BP) algorithm for decoding low-density parity-check (LDPC) codes. To lower the BP decoding complexity, both algorithms compute two magnitudes at each check node (CN) and pass them to the neighboring variable nodes (VNs).In this work we propose a new algorithm, ga-min*, that generalizes the MS and a-min* in terms of number of incoming messages to a CN.We analyze and demonstrate a condition to improve the performance when applying self-correction to the ga-min*. Simulations on 5G LDPC codes show that the proposed decoding algorithm yields comparable performance to the a-min* with a significant reduction in complexity, and it is robust against LLR mismatch.
Layered decoding is well appreciated in Low-Density Parity-Check (LDPC) decoder implementation since it provides efficient and high-throughput implementation of LDPC decoders. Variable-Node Layered Belief Propagation (VL-BP) algorithm and their reduced-complexity derivatives for LDPC codes are presented. The VL-BP algorithm is a modification of Belief Propagation algorithm (BP), where the variable nodes are divided in subgroups called layers and each iteration is broken into multiple sub-iterations. Some simplifications can also be made to lower the complexity of both BP and CL-BP algorithms, and particularly the complexity of the check node update rule. In this paper, we consider Variable Node Layered BP (VL-BP) algorithm and propose an optimized min-sum VL-BP (MS VL-BP) algorithm for decoding LDPC code which has better performance not only from MS VL-BP algorithm but also from BP algorithm. In this decoding method, unlike other layered algorithms, we consider for the first layer a set of variable nodes that has a low value of the intrinsic information. Simulation results show that good performance can be achieved, and which can even be improved by the addition of either a normalization term or an additive offset term.