Learning Disentangled Representations with Quantum Variational Autoencoders
Abstract
Variational autoencoders are powerful representation learning models that map complex data into low-dimensional latent spaces, enabling the discovery of interpretable and disentangled factors. Such representations can facilitate the interpretation and controllable generation of data describing complex scientific systems. Understanding how these factors are organized and encoded in latent space is therefore important for developing reliable representation learning models. Recently, quantum variational autoencoders (QVAEs) have been proposed as quantum representation models, demonstrating informative latent representations and improved latent-space occupancy through quantum regularization. However, it remains unclear whether and how QVAEs can learn disentangled and interpretable latent factors. A key challenge in investigating quantum latent factors is that a small number of qubits spans an exponentially large Hilbert space, making the notion of an individual quantum latent dimension nontrivial. Here, we investigate what constitutes an individual quantum latent dimension and whether it can encode a distinct factor. We develop theoretical insights into quantum latent dimensions and support them with empirical studies on representative synthetic problems, including MNIST variants. Across three datasets, we demonstrate that QVAEs can discover factorized and semantically interpretable latent representations, with individual qubits functioning as meaningful latent factors. These results establish a foundation for understanding quantum latent spaces and their potential for structured and interpretable representation learning.
Related
- Quantum Wavefunction Augmentation via Variational Autoencoders
- Elucidating structure-property correlations in ferroelectric Hf0.5Zr0.5O2 films using variational autoencoders
- Quantum Hierarchical Reinforcement Learning via Variational Quantum Circuits
- Hierarchical Fourier Approximation for Variational Quantum Distribution Learning
- Operator Learning with Variational Quantum Circuits
BibTeX
@misc{wang2026learning,
title = {{Learning Disentangled Representations with Quantum Variational Autoencoders}},
author = {Gaoyuan Wang and Jerry Tan and Mark Gerstein},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.07196},
eprint = {2610.07196},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.07196},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learning Disentangled Representations with Quantum Variational Autoencoders
AU - Gaoyuan Wang
AU - Jerry Tan
AU - Mark Gerstein
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.07196
UR - https://arxiv.org/abs/2610.07196
AB - Variational autoencoders are powerful representation learning models that map complex data into low-dimensional latent spaces, enabling the discovery of interpretable and disentangled factors. Such representations can facilitate the interpretation and controllable generation of data describing complex scientific systems. Understanding how these factors are organized and encoded in latent space is therefore important for developing reliable representation learning models. Recently, quantum variational autoencoders (QVAEs) have been proposed as quantum representation models, demonstrating informative latent representations and improved latent-space occupancy through quantum regularization. However, it remains unclear whether and how QVAEs can learn disentangled and interpretable latent factors. A key challenge in investigating quantum latent factors is that a small number of qubits spans an exponentially large Hilbert space, making the notion of an individual quantum latent dimension nontrivial. Here, we investigate what constitutes an individual quantum latent dimension and whether it can encode a distinct factor. We develop theoretical insights into quantum latent dimensions and support them with empirical studies on representative synthetic problems, including MNIST variants. Across three datasets, we demonstrate that QVAEs can discover factorized and semantically interpretable latent representations, with individual qubits functioning as meaningful latent factors. These results establish a foundation for understanding quantum latent spaces and their potential for structured and interpretable representation learning.
ER -