# Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling

arXiv: https://arxiv.org/abs/2606.13852 · HTML: https://mlsanity.com/paper/2606.13852/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 28 references that are in the map.
- First posted on arXiv 11 Jun 2026.

## Builds on (most cited first, 10 of 10)

- [Barren plateaus in quantum neural network training landscapes](https://mlsanity.com/paper/1803.11173/) (2018)
- [Topic Modeling in Embedding Spaces](https://mlsanity.com/paper/1907.04907/) (2019)
- [Autoencoding Variational Inference For Topic Models](https://mlsanity.com/paper/1703.01488/) (2017)
- [Implicit Reparameterization Gradients](https://mlsanity.com/paper/1805.08498/) (2018)
- [Discovering Discrete Latent Topics with Neural Variational Inference](https://mlsanity.com/paper/1706.00359/) (2017)
- [Quantum Variational Autoencoder](https://mlsanity.com/paper/1802.05779/) (2018)
- [Coherence-Aware Neural Topic Modeling](https://mlsanity.com/paper/1809.02687/) (2018)
- [vONTSS: vMF based semi-supervised neural topic modeling with optimal transport](https://mlsanity.com/paper/2307.01226/) (2023)
- [Quantum Transfer Learning for MNIST Classification Using a Hybrid Quantum-Classical Approach](https://mlsanity.com/paper/2408.03351/) (2024)
- [Analysing the Impact of Removing Infrequent Words on Topic Quality in LDA Models](https://mlsanity.com/paper/2311.14505/) (2023)

## Abstract (arXiv)

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 Cv 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.