Skip to main content

Pruning and Quantizing Neural Belief Propagation Decoders

Publication ,  Journal Article
Buchberger, A; Hager, C; Pfister, HD; Schmalen, L; Graell I Amat, A
Published in: IEEE Journal on Selected Areas in Communications
July 1, 2021

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.

Duke Scholars

Published In

IEEE Journal on Selected Areas in Communications

DOI

EISSN

1558-0008

ISSN

0733-8716

Publication Date

July 1, 2021

Volume

39

Issue

7

Start / End Page

1957 / 1966

Related Subject Headings

  • Networking & Telecommunications
  • 4606 Distributed computing and systems software
  • 4006 Communications engineering
  • 1005 Communications Technologies
  • 0906 Electrical and Electronic Engineering
  • 0805 Distributed Computing
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Buchberger, A., Hager, C., Pfister, H. D., Schmalen, L., & Graell I Amat, A. (2021). Pruning and Quantizing Neural Belief Propagation Decoders. IEEE Journal on Selected Areas in Communications, 39(7), 1957–1966. https://doi.org/10.1109/JSAC.2020.3041392
Buchberger, A., C. Hager, H. D. Pfister, L. Schmalen, and A. Graell I Amat. “Pruning and Quantizing Neural Belief Propagation Decoders.” IEEE Journal on Selected Areas in Communications 39, no. 7 (July 1, 2021): 1957–66. https://doi.org/10.1109/JSAC.2020.3041392.
Buchberger A, Hager C, Pfister HD, Schmalen L, Graell I Amat A. Pruning and Quantizing Neural Belief Propagation Decoders. IEEE Journal on Selected Areas in Communications. 2021 Jul 1;39(7):1957–66.
Buchberger, A., et al. “Pruning and Quantizing Neural Belief Propagation Decoders.” IEEE Journal on Selected Areas in Communications, vol. 39, no. 7, July 2021, pp. 1957–66. Scopus, doi:10.1109/JSAC.2020.3041392.
Buchberger A, Hager C, Pfister HD, Schmalen L, Graell I Amat A. Pruning and Quantizing Neural Belief Propagation Decoders. IEEE Journal on Selected Areas in Communications. 2021 Jul 1;39(7):1957–1966.

Published In

IEEE Journal on Selected Areas in Communications

DOI

EISSN

1558-0008

ISSN

0733-8716

Publication Date

July 1, 2021

Volume

39

Issue

7

Start / End Page

1957 / 1966

Related Subject Headings

  • Networking & Telecommunications
  • 4606 Distributed computing and systems software
  • 4006 Communications engineering
  • 1005 Communications Technologies
  • 0906 Electrical and Electronic Engineering
  • 0805 Distributed Computing