用10量子比特设备实现高效主题建模，混合量子经典架构性能超越现有模型。
Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling
- 在变分自编码器中嵌入量子电路，降低对硬件资源的需求
- 在AgNews数据集上达0.71的C_v和0.20的NPMI，主题多样性高
- 适合对量子增强机器学习感兴趣的研究者或算力受限场景
神经主题模型实现了可扩展的语义发现，但其与量子硬件的结合仍处于探索阶段。我们提出一种混合经典-量子变分自编码器（VAE）用于主题建模，在推理网络中嵌入参数化量子电路，同时保留经典的主题-词解码器。为应对量子硬件资源限制，我们设计了一种改进的高斯Softmax后验分布，将潜在空间维度与主题数量解耦，使模型可在仅10量子比特的低资源设备上运行。在AgNews数据集上，该混合VAE优于现有神经主题模型（NTMs），达到0.71的C_v一致性和0.20的NPMI得分，同时保持高主题多样性。我们还构建了全经典版本，同样在AgNews上表现更优，并在潜在空间中展现出清晰的类别分离。结果表明，即使在当前的噪声中等量子（NISQ）设备上，混合VAE也具备计算可行性，是量子增强主题建模的有前景方向。
原文摘要 · Abstract (English)
Neural topic models enable scalable semantic discovery, but their integration with quantum hardware remains largely unexplored. We present a proof-of-concept hybrid classical-quantum variational autoencoder (VAE) for topic modeling, embedding parameterized quantum circuits within the VAE inference network while retaining a classical topic-word decoder. To address the resource constraints of quantum hardware, we propose a modified Gaussian Softmax posterior that decouples latent space dimensionality from the number of topics to be extracted, enabling the model to operate with a low-resource 10-qubit quantum device. On the AgNews dataset, the hybrid VAE outperforms state-of-the-art neural topic models (NTMs), reaching a $C_v$ coherence score of 0.71 and an NPMI score of 0.20 while preserving high topic diversity. For comparison, we also construct a fully classical variant, which also outperforms state-of-the-art models on AgNews and exhibits clear class separation in the latent space. These results demonstrate that hybrid VAEs are computationally viable even on NISQ-era devices and represent a promising direction for quantum-enhanced topic modeling.
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。