A Low-Complexity Neural Normalized Min-Sum LDPC Decoding Algorithm Using Tensor-Train Decomposition

Liang, Yuanhui; Lam, Chan‐Tong; Ng, Benjamin K.

doi:10.1109/lcomm.2022.3207506

Cited by 10 publications

(22 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [16], we propose the NNMS+ algorithm, which uses different weight coefficients for different edges based on the NNMS algorithm [3]. In NNMS decoding algorithm, the calculation of messages from check nodes (CNs) to variable nodes (VNs) for iteration t, denoted u t c,v , is given as,…”

Section: Preliminaries a Tt-nnms+ Ldpc Decoding Algorithmmentioning

confidence: 99%

“…In [16], we modify the calculation of the messages from CNs to VNs for iteration t, denoted as U t c,v , by adding a variable weight vector, denoted as…”

Section: Preliminaries a Tt-nnms+ Ldpc Decoding Algorithmmentioning

confidence: 99%

“…In [15], TT was applied to a deep neural network (DNN) based channel estimator for the first time to address the challenge of time-varying channels in MIMO systems. In [16], we applied TT decomposition to the model-driven deep learning-based LDPC decoding algorithm, which significantly reduced the parameter storage requirements and computational complexity of the decoding algorithm. Compared with TT decomposition, TR decomposition has the property of permutation without deformation, and it is more flexible and convenient in the selection of rank.…”

Section: Introductionmentioning

confidence: 99%

“…• We apply TR decomposition to the NNMS+ decoding algorithm proposed in [16] to further reduce its computational complexity, called TR-NNMS+ algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…Compared with Tensor-Train (TT) decomposition, TR decomposition is more flexible for the selection of ranks, and is also conducive to the use of rank optimization algorithms. In particular, we use TR decomposition to decompose not only the weight parameter matrix of Neural Normalized Min-Sum (NNMS)+ algorithm [16], but also the message matrix transmitted between variable nodes and check nodes. Furthermore, we combine the TR decomposition and temporal and spatial weight sharing algorithm, called joint-way compression, to further lower the complexity of LDPC neural decoding algorithm.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Joint-Way Compression for LDPC Neural Decoding Algorithm With Tensor-Ring Decomposition

Liang

Lam

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

In this paper, we propose low complexity joint-way compression algorithms with Tensor-Ring (TR) decomposition and weight sharing to further lower the storage and computational complexity requirements for low density parity check (LDPC) neural decoding. Compared with Tensor-Train (TT) decomposition, TR decomposition is more flexible for the selection of ranks, and is also conducive to the use of rank optimization algorithms. In particular, we use TR decomposition to decompose not only the weight parameter matrix of Neural Normalized Min-Sum (NNMS)+ algorithm [16], but also the message matrix transmitted between variable nodes and check nodes. Furthermore, we combine the TR decomposition and temporal and spatial weight sharing algorithm, called joint-way compression, to further lower the complexity of LDPC neural decoding algorithm. We show that the joint-way compression algorithm can achieve better compression efficiency than a single compression algorithm, while maintaining a comparable bit error rate (BER) performance. From the numerical experiments, we found that all the compression algorithms with appropriate selection of ranks give almost no performance BER degradation and that the TRwm-ssNNMS+ algorithm, which combines the spatial sharing and TR decomposition of both weight and message matrix, has the best compression performance. Comparing with our TT-NNMS+ algorithm proposed in [16], the number of parameters is reduced by about 70 times and the number of multiplications is reduced by about 6 times.

show abstract

Section: Preliminaries a Tt-nnms+ Ldpc Decoding Algorithmmentioning

confidence: 99%

“…In [16], we modify the calculation of the messages from CNs to VNs for iteration t, denoted as U t c,v , by adding a variable weight vector, denoted as…”

Section: Preliminaries a Tt-nnms+ Ldpc Decoding Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…• We apply TR decomposition to the NNMS+ decoding algorithm proposed in [16] to further reduce its computational complexity, called TR-NNMS+ algorithm.…”

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Joint-Way Compression for LDPC Neural Decoding Algorithm With Tensor-Ring Decomposition

Liang

Lam

2023

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

Security Gap Improvement of BICM Systems Through Bit-Labeling Optimization for the Gaussian Wiretap Channel

2022

View full text Add to dashboard Cite

This paper provides a comprehensive survey on recent advances in deep learning (DL) techniques for the channel coding problems. Inspired by the recent successes of DL in a variety of research domains, its applications to the physical layer technologies have been extensively studied in recent years, and are expected to be a potential breakthrough in supporting the emerging use cases of the next generation wireless communication systems such as 6G. In this paper, we focus exclusively on the channel coding problems and review existing approaches that incorporate advanced DL techniques into code design and channel decoding. After briefly introducing the background of recent DL techniques, we categorize and summarize a variety of approaches, including model-free and mode-based DL, for the design and decoding of modern error-correcting codes, such as low-density parity check (LDPC) codes and polar codes, to highlight their potential advantages and challenges. Finally, the paper concludes with a discussion of open issues and future research directions in channel coding.

show abstract

Hypernetwork Based Model-Driven Channel Neural Decoding

Liang,

Lam,

et al. 2024

IEEE Access

Self Cite

View full text Add to dashboard Cite

Channel decoding algorithms based on model-driven deep learning, also known as channel neural decoding algorithms, have received a lot of attention in recent years. However, the internal parameters and number of layers of the current channel neural decoding algorithm cannot be changed after training. Once changed, retraining of the channel neural decoding network is required. Hypernetwork is a neural network that can generate internal parameters for the main neural network to reduce the training cost of the main neural network and improve the flexibility of the main neural network. In this study, a novel hypernetwork based channel neural decoder is proposed for neural belief propagation algorithms (NBP), including the neural normalized min-sum (NNMS) and neural offset min-sum (NOMS) algorithm. According to the type of information interaction between the hypernetwork and the main decoding network, hypernetwork-based channel neural decoders can be divided into two types: static and dynamic. The internal parameters of the static hypernetwork-based channel neural decoder can be updated as needed without retraining of the main network. In addition to this benefit, the number of layers of the dynamic hypernetwork-based channel neural decoder can also be adjusted. Experimental results show that, compared with the existing NNMS decoding algorithms, the proposed hypernetwork-based NNMS decoding algorithms can achieve better performance on both low-density parity-check (LDPC) and Bose-Chaudhuri-Hocquenghem (BCH) codes.

show abstract

A Low-Complexity Neural Normalized Min-Sum LDPC Decoding Algorithm Using Tensor-Train Decomposition

Cited by 10 publications

References 10 publications

Joint-Way Compression for LDPC Neural Decoding Algorithm With Tensor-Ring Decomposition

Joint-Way Compression for LDPC Neural Decoding Algorithm With Tensor-Ring Decomposition

Security Gap Improvement of BICM Systems Through Bit-Labeling Optimization for the Gaussian Wiretap Channel

Hypernetwork Based Model-Driven Channel Neural Decoding

Contact Info

Product

Resources

About