Hybrid Classical-Quantum Variational Autoencoder for Neural Topic Modeling
Quick Answer
This paper shows that The hybrid classical-quantum variational autoencoder (VAE) demonstrates superior performance in topic modeling, achieving a $C_v$ coherence score of 0.71 and an NPMI score of 0.20 on the AgNews dataset.
Quick Take
This model effectively integrates parameterized quantum circuits within a classical framework, proving viable on low-resource 10-qubit devices and outperforming state-of-the-art neural topic models.
Key Points
- Hybrid VAE integrates quantum circuits within a classical topic-word decoder.
- Achieved $C_v$ coherence score of 0.71 and NPMI score of 0.20 on AgNews.
- Outperformed state-of-the-art neural topic models while maintaining topic diversity.
- Modified Gaussian Softmax posterior allows operation on low-resource quantum devices.
- Demonstrates computational viability for quantum-enhanced topic modeling.
Paper Resources
Source Excerpt
arXiv:2606. 13852v1 Announce Type: new Abstract: 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. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.