Application of Tensor Decomposition to Reduce the Complexity of Neural Min-Sum Channel Decoding Algorithm
Source abstract
Abstract
Channel neural decoding is very promising as it outperforms the traditional channel decoding algorithms. Unfortunately, it still faces the disadvantage of high computational complexity and storage complexity compared with the traditional decoding algorithms. In this paper, we propose that low rank decomposition techniques based on tensor train decomposition and tensor ring decomposition can be utilized in neural offset min-sum (NOMS) and neural scale min-sim (NSMS) decoding algorithms. The experiment results show that the proposed two algorithms achieve near state-of-the-art performance with low complexity.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Tensor decomposition and applications · Blind Source Separation Techniques · Algorithms and Data Compression
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Applied Sciences, Macao Polytechnic University, Macao 999078, China
BUPT Network Information Center, Beijing University of Posts and Telecommunications, Beijing 100876, China
Funding
Macao Polytechnic University, Macao SAR, China
References (25)
Show source-provided references
1. Nachmani, E., Be’ery, Y., and Burshtein, D. (2016, January 27–30). Learning to decode linear codes using deep learning. Proceedings of the 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton), Monticello, IL, USA.10.1109/ALLERTON.2016.7852251 ↗
2. Nachmani, E., Marciano, E., Burshtein, D., and Be’ery, Y. (2017). Rnn decoding of linear block codes. arXiv.
3. Deep learning methods for improved decoding of linear codes10.1109/JSTSP.2017.2788405 ↗
4. Qingle, W., Su-Kit, T.A.N.G., Liang, Y., Lam, C.T., and Yan, M. (2021, January 23–26). A low complexity model-driven deep learning ldpc decoding algorithm. Proceedings of the 2021 IEEE 6th International Conference on Computer and Communication Systems (ICCCS), Chengdu, China.
5. Tran-Thi, B.N., Nguyen-Ly, T.T., Hong, H.N., and Hoang, T. (2021, January 15–16). An improved offset min-sum ldpc decoding algorithm for 5 g new radio. Proceedings of the 2021 International Symposium on Electrical and Electronics Engineering (ISEE), Ho Chi Minh, Vietnam.10.1109/ISEE51682.2021.9418782 ↗
6. Learning to decode protograph ldpc codes10.1109/JSAC.2021.3078488 ↗
7. Chen, C., Xu, Y., Ju, H., He, D., Zhang, W., and Zhang, Y. (2018, January 6–8). Variable correction for min-sum ldpc decoding applied in atsc3.0. Proceedings of the 2018 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB), Valencia, Spain.10.1109/BMSB.2018.8436894 ↗
8. Tensor-train decomposition10.1137/090752286 ↗
9. Tensorizing neural networks
10. Zhao, Q., Sugiyama, M., Yuan, L., and Cichocki, A. (2019, January 12–17). Learning efficient tensor representations with ring-structured networks. Proceedings of the ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.10.1109/ICASSP.2019.8682231 ↗
11. A highly parallel and energy efficient three-dimensional multilayer cmos-rram accelerator for tensorized neural network10.1109/TNANO.2017.2732698 ↗
12. Su, J., Li, J., Bhattacharjee, B., and Huang, F. (2018). Tensorial neural networks: Generalization of neural networks and application to model compression. arXiv.
13. Garipov, T., Podoprikhin, D., Novikov, A., and Vetrov, D. (2016). Ultimate tensorization: Compressing convolutional and fc layers alike. arXiv.
14. Tjandra, A., Sakti, S., and Nakamura, S. (2017, January 14–19). Compressing recurrent neural network with tensor train. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN), Anchorage, AK, USA.10.1109/IJCNN.2017.7966420 ↗
15. Tjandra, A., Sakti, S., and Nakamura, S. (2018, January 8–13). Tensor decomposition for compressing recurrent neural network. Proceedings of the 2018 International Joint Conference on Neural Networks (IJCNN), Rio de Janeiro, Brazil.10.1109/IJCNN.2018.8489213 ↗
16. Zhao, Q., Zhou, G., Xie, S., Zhang, L., and Cichocki, A. (2016). Tensor ring decomposition. arXiv.
17. Pan, Y., Xu, J., Wang, M., Ye, J., Wang, F., Bai, K., and Xu, Z. (February, January 27). Compressing recurrent neural networks with tensor ring for action recognition. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
18. Wang, W., Sun, Y., Eriksson, B., Wang, W., and Aggarwal, V. (2018, January 18–23). Wide compression: Tensor ring nets. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, UT, USA.
19. Li, X.P., Liu, Q., and So, H.C. (2021). Nonlinear tensor ring network. arXiv.
20. A low-complexity neural normalized min-sum ldpc decoding algorithm using tensor-train decomposition10.1109/LCOMM.2022.3207506 ↗
21. Wang, Q., Wang, S., Fang, H., Chen, L., Chen, L., and Guo, Y. (2020, January 7–11). A model-driven deep learning method for normalized min-sum ldpc decoding. Proceedings of the 2020 IEEE International Conference on Communications Workshops (ICC Workshops), Virtually.10.1109/ICCWorkshops49005.2020.9145237 ↗
22. Lugosch, L., and Gross, W.J. (2017, January 25–30). Neural offset min-sum decoding. Proceedings of the 2017 IEEE International Symposium on Information Theory (ISIT), Aachen, Germany.10.1109/ISIT.2017.8006751 ↗
23. A constructive algorithm for decomposing a tensor into a finite sum of orthonormal rank-1 terms10.1137/141000658 ↗
24. Lugosch, L., and Gross, W.J. (2018, January 28–31). Learning from the syndrome. Proceedings of the 2018 52nd Asilomar Conference on Signals, Systems, and Computers, Grove, CA, USA.10.1109/ACSSC.2018.8645388 ↗
25. Tensorly: Tensor learning in python