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

ICT Express

Learning strategies for neural min-sum decoding of LDPC codes

Hyeyeon Na, Hosung Park, Hee-Youl Kwak, Seok-Ki Ahn

Published Jan 6, 2025• 5 citations
Publisher

Abstract

The min-sum (MS) decoding for low-density parity-check codes, though less complex than the sum–product algorithm, suffers from worse error-correcting performance. For enhancement, neural MS decoders leveraging deep learning have recently been introduced, but how to train them has not been sufficiently discussed. In this paper, we propose a novel dataset construction method and also propose systematic learning strategies by finding a good combination of dataset composition, loss functions, weight sharing, weight assignment , and weight update method. Simulations demonstrate that the proposed method achieves better error-correcting performance than other works, especially in the error floor region, within a limited number of iterations.

DOI
10.1016/j.icte.2024.09.010

Related papers

Learning to Decode Protograph LDPC Codes

Jincheng Dai, Kailin Tan, Zhongwei Si +4 more

The recent development of deep learning methods provides a new approach to optimize the belief propagation (BP) decoding of linear codes. However, the limitation of existing works is that the scale of neural networks increases rapidly with the codelength, thus they can only support short to moderate codelengths. From the point view of practicality, we propose a high-performance neural min-sum (MS) decoding method that makes full use of the lifting structure of protograph low-density parity-check (LDPC) codes. By this means, the size of the parameter array of each layer in the neural decoder only equals the number of edge-types for arbitrary codelengths. In particular, for protograph LDPC codes, the proposed neural MS decoder is constructed in a special way such that identical parameters are shared by a bundle of edges derived from the same edge-type. To reduce the complexity and overcome the vanishing gradient problem in training the proposed neural MS decoder, an iteration-by-iteration (i.e., layer-by-layer in neural networks) greedy training method is proposed. With this, the proposed neural MS decoder tends to be optimized with faster convergence, which is aligned with the early termination mechanism widely used in practice. To further enhance the generalization ability of the proposed neural MS decoder, a codelength/rate compatible training method is proposed, which randomly selects samples from a set of codes lifted from the same base code. As a theoretical performance evaluation tool, a trajectory-based extrinsic information transfer (T-EXIT) chart is developed for various decoders. Both T-EXIT and simulation results show that the optimized MS decoding can provide faster convergence and up to 1dB gain compared with the plain MS decoding and its variants with only slightly increased complexity. In addition, it can even outperform the sum-product algorithm for some short codes.

arXiv:2102.03828•IEEE Journal on Selected Areas in Communications•May 10, 2021•80 citations

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

Hee-Youl Kwak, Dae-Young Yun, Yongjune Kim +2 more

Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level, presents challenges for achieving extremely low error rates and deploying LDPC codes in scenarios demanding ultra-high reliability. In this work, we propose training methods for neural min-sum (NMS) decoders to eliminate the error-floor effect. First, by leveraging the boosting learning technique of ensemble networks, we divide the decoding network into two neural decoders and train the post decoder to be specialized for uncorrected words that the first decoder fails to correct. Secondly, to address the vanishing gradient issue in training, we introduce a block-wise training schedule that locally trains a block of weights while retraining the preceding block. Lastly, we show that assigning different weights to unsatisfied check nodes effectively lowers the error-floor with a minimal number of weights. By applying these training methods to standard LDPC codes, we achieve the best error-floor performance compared to other decoding methods. The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor .

arXiv:2310.07194•neural information processing systems•Jan 1, 2023•11 citations

Normalized Min-Sum Neural Network for LDPC Decoding

Qing Wang, Qing Liu, Shunfu Wang +5 more

The success of deep learning has encouraged its applications in decoding error-correcting codes, e.g., LDPC decoding. In this paper, we propose a model-driven deep learning method for normalized min-sum (NMS) low-density parity-check (LDPC) decoding, namely neural NMS (NNMS) LDPC decoding network. By unfolding the iterative decoding progress between checking nodes (CNs) and variable nodes (VNs) into a feed-forward propagation network, we can harvest the benefits of both the model-driven deep learning and the conventional normalized min-sum (NMS) LDPC decoding method. In addition, we proposed a shared parameters NNMS with the LeakyReLU and a 12-bit quantizer (SNNMS-LR-Q) which reduces the number of required multipliers and correction factors by sharing parameters, increasing the nonlinear fitting ability by adding LeakyReLU. By utilizing the 12-bit quantizer, we can improve the confrontation ability. Thorough experiments with different code lengths, code rates, channel conditions, and check matrices are implemented to demonstrate the advantages and robustness of our proposed networks. The BER performance of the proposed NNMS is 1.5 dB better than the NMS, using fewer iterations. Meanwhile, The SNNMS-LR-Q outperforms the NNMS regarding the BER performance and efficiency.

IEEE Transactions on Cognitive Communications and Networking•Oct 6, 2022•31 citations

A Model-Driven Deep Learning Method for Normalized Min-Sum LDPC Decoding

Qing Wang, Shunfu Wang, Haoyu Fang +3 more

With the applications of deep learning networks booming in physical layer communication, deep-learning-based channel decoding methods have become a research hotspot. However, the high complexity hinders the application of deep neural network (DNN) on long code. In this paper, we propose a model-driven deep learning method for normalized min-sum (NMS) low-density parity-check (LDPC) decoding. First, we propose a neural normalized min-sum (NNMS) LDPC decoding network. By unfolding the iterative decoding progress between checking nodes (CNs) and variable nodes (VNs) into a feedforward propagation network, we can make use of the advantages of both model-driven deep learning methods and conventional normalized min-sum (CNMS) LDPC decoding method. Second, considering that the NNMS decoder needs large number of multipliers, we propose a shared neural normalized min-sum (SNNMS) decoding network to reduce the number of correction factors. Experimental results show that the BER performance of the proposed NNMS decoder is 1.5dB better than the conventional LDPC decoder, using fewer iterations. Furthermore, the proposed SNNMS decoder outperforms the proposed NNMS decoder and reduces the computation complexity.

IEEE International Conference on Communications workshops•Jun 1, 2020•48 citations

Learning to Decode Non-Binary LDPC Codes

Yujie Tian, Xinyi Sui, Zhongwei Si

We propose a neural min-sum (MS) decoder for non-binary LDPC codes by applying deep learning to the decoding with short to moderate code lengths. In this algorithm, the iterations are unfolded into hidden layers of the neural network, and trainable weights are added to the check node updates to mitigate the correlation in the message passing due to short girths in the Tanner graph. To avoid gradient vanishing and to converge faster, we adopt an iterative training mechanism for parameter tuning. Furthermore, we investigate the impact of girth distribution on the proposed neural MS decoder, which reveals the reasons for the expected performance improvement. Numerical results in terms of bit error rate are provided, which show that the neural MS decoder achieves significant gains for decoding non-binary LDPC codes.

IEEE Wireless Communications and Networking Conference•Mar 24, 2025•0 citations

A Deep Learning-Aided Post-Processing Scheme to Lower the Error Floor of LDPC Codes

Jiajun He

Low-density parity-check (LDPC) codes are widely used in a variety of communication systems because of their low complexity iterative decoding and performance approaching Shannon capacity. However, the existence of error floor seriously hinders the application and development of LDPC codes in related fields. In this paper, a deep learning-aided post-processing scheme (DLAPPS) based on Layered Normalized Min-Sum algorithm (LNMSA) is proposed to effectively lower error floor of LDPC codes. LNMSA is used in the first stage, and in the second stage incorrect frames are re-decoded by processing two types of nodes classified by neural networks. Simulation results show that the proposed DLAPPS can significantly improve error correction performance and lower the error floor of LDPC codes while maintaining a relatively low decoding complexity.

IEEE International Conference on Communication Technology (ICCT)•Oct 28, 2020•4 citations
The min-sum (MS) decoding for low-density parity-check codes, though less complex than the sum–product algorithm, suffers from worse error-correcting performance. For enhancement, neural MS decoders leveraging deep learning have recently been introduced, but how to train them has not been sufficiently discussed. In this paper, we propose a novel dataset construction method and also propose systematic learning strategies by finding a good combination of dataset composition, loss functions, weight sharing, weight assignment , and weight update method. Simulations demonstrate that the proposed method achieves better error-correcting performance than other works, especially in the error floor region, within a limited number of iterations.
The recent development of deep learning methods provides a new approach to optimize the belief propagation (BP) decoding of linear codes. However, the limitation of existing works is that the scale of neural networks increases rapidly with the codelength, thus they can only support short to moderate codelengths. From the point view of practicality, we propose a high-performance neural min-sum (MS) decoding method that makes full use of the lifting structure of protograph low-density parity-check (LDPC) codes. By this means, the size of the parameter array of each layer in the neural decoder only equals the number of edge-types for arbitrary codelengths. In particular, for protograph LDPC codes, the proposed neural MS decoder is constructed in a special way such that identical parameters are shared by a bundle of edges derived from the same edge-type. To reduce the complexity and overcome the vanishing gradient problem in training the proposed neural MS decoder, an iteration-by-iteration (i.e., layer-by-layer in neural networks) greedy training method is proposed. With this, the proposed neural MS decoder tends to be optimized with faster convergence, which is aligned with the early termination mechanism widely used in practice. To further enhance the generalization ability of the proposed neural MS decoder, a codelength/rate compatible training method is proposed, which randomly selects samples from a set of codes lifted from the same base code. As a theoretical performance evaluation tool, a trajectory-based extrinsic information transfer (T-EXIT) chart is developed for various decoders. Both T-EXIT and simulation results show that the optimized MS decoding can provide faster convergence and up to 1dB gain compared with the plain MS decoding and its variants with only slightly increased complexity. In addition, it can even outperform the sum-product algorithm for some short codes.
Low-density parity-check (LDPC) codes have been successfully commercialized in communication systems due to their strong error correction capabilities and simple decoding process. However, the error-floor phenomenon of LDPC codes, in which the error rate stops decreasing rapidly at a certain level, presents challenges for achieving extremely low error rates and deploying LDPC codes in scenarios demanding ultra-high reliability. In this work, we propose training methods for neural min-sum (NMS) decoders to eliminate the error-floor effect. First, by leveraging the boosting learning technique of ensemble networks, we divide the decoding network into two neural decoders and train the post decoder to be specialized for uncorrected words that the first decoder fails to correct. Secondly, to address the vanishing gradient issue in training, we introduce a block-wise training schedule that locally trains a block of weights while retraining the preceding block. Lastly, we show that assigning different weights to unsatisfied check nodes effectively lowers the error-floor with a minimal number of weights. By applying these training methods to standard LDPC codes, we achieve the best error-floor performance compared to other decoding methods. The proposed NMS decoder, optimized solely through novel training methods without additional modules, can be integrated into existing LDPC decoders without incurring extra hardware costs. The source code is available at https://github.com/ghy1228/LDPC_Error_Floor .
The success of deep learning has encouraged its applications in decoding error-correcting codes, e.g., LDPC decoding. In this paper, we propose a model-driven deep learning method for normalized min-sum (NMS) low-density parity-check (LDPC) decoding, namely neural NMS (NNMS) LDPC decoding network. By unfolding the iterative decoding progress between checking nodes (CNs) and variable nodes (VNs) into a feed-forward propagation network, we can harvest the benefits of both the model-driven deep learning and the conventional normalized min-sum (NMS) LDPC decoding method. In addition, we proposed a shared parameters NNMS with the LeakyReLU and a 12-bit quantizer (SNNMS-LR-Q) which reduces the number of required multipliers and correction factors by sharing parameters, increasing the nonlinear fitting ability by adding LeakyReLU. By utilizing the 12-bit quantizer, we can improve the confrontation ability. Thorough experiments with different code lengths, code rates, channel conditions, and check matrices are implemented to demonstrate the advantages and robustness of our proposed networks. The BER performance of the proposed NNMS is 1.5 dB better than the NMS, using fewer iterations. Meanwhile, The SNNMS-LR-Q outperforms the NNMS regarding the BER performance and efficiency.
With the applications of deep learning networks booming in physical layer communication, deep-learning-based channel decoding methods have become a research hotspot. However, the high complexity hinders the application of deep neural network (DNN) on long code. In this paper, we propose a model-driven deep learning method for normalized min-sum (NMS) low-density parity-check (LDPC) decoding. First, we propose a neural normalized min-sum (NNMS) LDPC decoding network. By unfolding the iterative decoding progress between checking nodes (CNs) and variable nodes (VNs) into a feedforward propagation network, we can make use of the advantages of both model-driven deep learning methods and conventional normalized min-sum (CNMS) LDPC decoding method. Second, considering that the NNMS decoder needs large number of multipliers, we propose a shared neural normalized min-sum (SNNMS) decoding network to reduce the number of correction factors. Experimental results show that the BER performance of the proposed NNMS decoder is 1.5dB better than the conventional LDPC decoder, using fewer iterations. Furthermore, the proposed SNNMS decoder outperforms the proposed NNMS decoder and reduces the computation complexity.
We propose a neural min-sum (MS) decoder for non-binary LDPC codes by applying deep learning to the decoding with short to moderate code lengths. In this algorithm, the iterations are unfolded into hidden layers of the neural network, and trainable weights are added to the check node updates to mitigate the correlation in the message passing due to short girths in the Tanner graph. To avoid gradient vanishing and to converge faster, we adopt an iterative training mechanism for parameter tuning. Furthermore, we investigate the impact of girth distribution on the proposed neural MS decoder, which reveals the reasons for the expected performance improvement. Numerical results in terms of bit error rate are provided, which show that the neural MS decoder achieves significant gains for decoding non-binary LDPC codes.
Low-density parity-check (LDPC) codes are widely used in a variety of communication systems because of their low complexity iterative decoding and performance approaching Shannon capacity. However, the existence of error floor seriously hinders the application and development of LDPC codes in related fields. In this paper, a deep learning-aided post-processing scheme (DLAPPS) based on Layered Normalized Min-Sum algorithm (LNMSA) is proposed to effectively lower error floor of LDPC codes. LNMSA is used in the first stage, and in the second stage incorrect frames are re-decoded by processing two types of nodes classified by neural networks. Simulation results show that the proposed DLAPPS can significantly improve error correction performance and lower the error floor of LDPC codes while maintaining a relatively low decoding complexity.