Threshold-Controlled Residual Decoding for LDPC Codes via a Weight-Shared Neural Network
IEEE Communications Letters · 2026 · 30 · 2904-2908
DOI: 10.1109/lcomm.2026.3721615 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Hua Zhou und 1 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
This letter addresses the issues of gradient vanishing and performance degradation in deep-unfolded neural LDPC decoders. We introduce a residual-based and weight-shared neural normalized min-sum (RSNNMS) decoder, which incorporates residual connections into the shared neural NMS (SNNMS) architecture to actively leverage messages from prior iterations, thereby enhancing current layer updates and stabilizing training in deep networks. Observing that the residual weights learned by RSNNMS exhibit varying contributions across different layers, we further propose a threshold-controlled variant (TRSNNMS) that applies a threshold during inference obtained on the validation data set to selectively enable residual connections based on their significance, thereby reducing computational complexity while further improving decoding performance. Simulation results for an LDPC code with block length 576 and code rate 0.75 demonstrate that, at a bit error rate (BER) of $10^{-6}$ , the RSNNMS decoder achieves approximately 0.26 dB signal-to-noise ratio (SNR) gain over the SNNMS decoder, and the TRSNNMS decoder yields an additional 0.22 dB gain over RSNNMS.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhou, H., & Zhang, L. (2026). Threshold-Controlled Residual Decoding for LDPC Codes via a Weight-Shared Neural Network. IEEE Communications Letters, 30, 2904-2908. https://doi.org/10.1109/lcomm.2026.3721615
Vancouver
Zhou H, Zhang L. Threshold-Controlled Residual Decoding for LDPC Codes via a Weight-Shared Neural Network. IEEE Communications Letters. 2026;30:2904-2908. doi:10.1109/lcomm.2026.3721615
BibTeX
@article{Zhou2026,
author = {Zhou, Hua and Zhang, Likang},
title = {Threshold-Controlled Residual Decoding for LDPC Codes via a Weight-Shared Neural Network},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {2904--2908},
doi = {10.1109/lcomm.2026.3721615}
}
EUVIMED