{"slug": "hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling", "title": "Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling", "summary": "Researchers introduced a hybrid classical-quantum variational autoencoder for neural topic modeling, embedding parameterized quantum circuits in the inference network while retaining a classical decoder. The model achieved state-of-the-art coherence scores on the AgNews dataset using a 10-qubit quantum device, demonstrating viability on NISQ-era hardware.", "body_md": "arXiv:2606.13852v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling", "canonical_source": "https://arxiv.org/abs/2606.13852", "published_at": "2026-06-15 04:00:00+00:00", "updated_at": "2026-06-15 04:16:38.205401+00:00", "lang": "en", "topics": ["machine-learning", "artificial-intelligence", "natural-language-processing"], "entities": ["AgNews"], "alternates": {"html": "https://wpnews.pro/news/hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling", "markdown": "https://wpnews.pro/news/hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling.md", "text": "https://wpnews.pro/news/hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling.txt", "jsonld": "https://wpnews.pro/news/hybrid-classical-quantum-variational-autoencoder-for-neural-topic-modeling.jsonld"}}