Enhancing interpretability in generative modeling: statistically disentangled latent spaces guided by generative factors in scientific datasets

• Published in: Machine learning Vol. 114; no. 9; p. 197
• Main Authors: Ganguli, Arkaprabha, Ramachandra, Nesar, Bessac, Julie, Constantinescu, Emil
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2025; Springer Nature B.V
• Subjects: Accuracy; Artificial Intelligence; Computer Science; Control; Datasets; Independent variables; Machine Learning; Mechatronics; Natural Language Processing (NLP); Physical factors; Robotics; Simulation and Modeling; Subject specialists; Variables; Representation learning; Variational autoencoder; Disentangled generative factors; Posterior regularization
• ISSN: 0885-6125; 1573-0565
• DOI: 10.1007/s10994-025-06816-y

This study addresses the challenge of statistically extracting generative factors from complex, high-dimensional datasets in unsupervised or semi-supervised settings. We investigate encoder–decoder-based generative models for nonlinear dimensionality reduction, focusing on disentangling low-dimensional latent variables corresponding to independent physical factors. Introducing Aux-VAE, a novel architecture within the classical Variational Autoencoder framework, we achieve disentanglement with minimal modifications to the standard VAE loss function by leveraging prior statistical knowledge through auxiliary variables. These variables guide the shaping of the latent space by aligning latent factors with learned auxiliary variables. We validate the efficacy of Aux-VAE through comparative assessments on multiple datasets, including astronomical simulations.