用渐进训练让神经网络学会高效纠错编码
Learning Binary Autoencoder-Based Codes with Progressive Training
- 先连续预训练再直接二值化，避开梯度近似难题
- 在7,4码上达到与最优汉明码相同的错误率
- 适合想用神经网络学经典纠错码的研究者
纠错码在数字通信中至关重要，可确保信息在信道干扰下仍能准确恢复。近年来，基于自编码器（AE）的端到端通信系统设计受到关注，为传统编码方案提供了数据驱动替代。然而，在可微分的AE架构中强制二进制码字仍具挑战，因离散化会破坏梯度传播，常导致收敛不稳定。为此，本文提出一种简化的两阶段训练流程：先进行连续预训练，再直接二值化并微调，无需梯度近似技术。在二进制对称信道（BSC）上的(7,4)分组码配置下，所学习的编码器-解码器对生成了最优汉明码的旋转版本（陪集码），自然恢复其线性与距离特性，从而实现与最大似然（ML）解码相同的块错误率（BLER）。结果表明，紧凑的AE架构可通过稳定且直接的训练过程有效学习结构化、代数最优的二进制码。
原文摘要 · Abstract (English)
Error correcting codes play a central role in digital communication, ensuring that transmitted information can be accurately reconstructed despite channel impairments. Recently, autoencoder (AE) based approaches have gained attention for the end-to-end design of communication systems, offering a data driven alternative to conventional coding schemes. However, enforcing binary codewords within differentiable AE architectures remains difficult, as discretization breaks gradient flow and often leads to unstable convergence. To overcome this limitation, a simplified two stage training procedure is proposed, consisting of a continuous pretraining phase followed by direct binarization and fine tuning without gradient approximation techniques. For the (7,4) block configuration over a binary symmetric channel (BSC), the learned encoder-decoder pair learns a rotated version (coset code) of the optimal Hamming code, naturally recovering its linear and distance properties and thereby achieving the same block error rate (BLER) with maximum likelihood (ML) decoding. These results indicate that compact AE architectures can effectively learn structured, algebraically optimal binary codes through stable and straightforward training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。