Graph Attention Network-Aided Message-Passing Neural Decoder for Polar Codes Based on Sparse-Pruned Tanner Graphs
IEEE Communications Letters · 2026 · 30 · 1920-1924
DOI: 10.1109/lcomm.2026.3687553 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Dongrui Fu und 4 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Gefördert von: Guangxi Science and Technology Base and Talent Special Project, National Natural Science Foundation of China, Natural Science Foundation of Guangxi Province.
Abstract (Originalsprache)
In this letter, we propose a fully trainable graph neural network (GNN) decoder for short polar codes, underpinned by a novel graph attention network (GAT)-aided message-passing (GAT-MP) framework. This framework aligns message passing neural network (MPNN) with the belief propagation (BP) algorithm, leveraging graph attention mechanism to enhance the decoding process. To facilitate effective learning, we introduce a tailored two-stage train-then-fine-tune (TTF) methodology, alongside a specialized training algorithm. Simulation results show that the proposed method significantly outperforms advanced BP decoders while offering competitive complexity. Furthermore, it matches or exceeds the performance of successive-cancellation list (SCL) and state-of-the-art (SOTA) Transformer-based methods, with a significantly smaller model size than the latter.
Förderung
- Guangxi Science and Technology Base and Talent Special Project
- National Natural Science Foundation of China
- Natural Science Foundation of Guangxi Province
Zitieren
APA
Fu, D., Sun, Y., Li, X., Dang, S., & Chen, H. (2026). Graph Attention Network-Aided Message-Passing Neural Decoder for Polar Codes Based on Sparse-Pruned Tanner Graphs. IEEE Communications Letters, 30, 1920-1924. https://doi.org/10.1109/lcomm.2026.3687553
Vancouver
Fu D, Sun Y, Li X, Dang S, Chen H. Graph Attention Network-Aided Message-Passing Neural Decoder for Polar Codes Based on Sparse-Pruned Tanner Graphs. IEEE Communications Letters. 2026;30:1920-1924. doi:10.1109/lcomm.2026.3687553
BibTeX
@article{Fu2026,
author = {Fu, Dongrui and Sun, Youming and Li, Xiangcheng and Dang, Shuping and Chen, Haiqiang},
title = {Graph Attention Network-Aided Message-Passing Neural Decoder for Polar Codes Based on Sparse-Pruned Tanner Graphs},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {1920--1924},
doi = {10.1109/lcomm.2026.3687553}
}
EUVIMED