arXiv cs.AI· Samira Malek·· 12 小时前AI 评分18
GBPNet：用广义置信传播网络学习线性码解码
Learning to Decode Linear Codes with Generalized Belief Propagation Network
AI 导读
研究者提出广义置信传播网络（GBPNet），在保留 Tanner 图结构与消息传递对称性的同时，通过级联变量节点更新和可学习的逐元素消息缩放增强解码器学习能力。该工作还引入渐进训练与高 SNR 训练两种策略提升解码准确率。在多种线性码上的实验显示，GBPNet 的误码率低于传统置信传播及所评估的当前最优神经解码器。
正文 · 原文
Abstract:Error correcting codes are a fundamental component of communication systems, enabling reliable data transmission over noisy channels. Recently, neural decoders have demonstrated notable performance gains over classical iterative algorithms. In this paper, we propose a Generalized Belief Propagation Network (GBPNet) that preserves message-passing symmetry while enhancing the decoder's learning capability. The architecture uses cascaded variable-node updates and learned element-wise message scaling while retaining the Tanner graph structure. We also introduce two training strategies, progressive training and high-SNR training, that improve decoding accuracy. Experimental results on several linear codes show that GBPNet achieves lower bit error rates than conventional belief propagation and the evaluated state-of-the-art neural decoders.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.06874 [cs.AI] |
| (or arXiv:2611.06874v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.06874 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Samira Malek [view email]
[v1]
Wed, 4 Nov 2026 18:29:31 UTC (1,036 KB)
来源：arXiv cs.AI · arxiv.org