Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets

• URL: http://arxiv.org/abs/2507.00298v1
• Date: Mon, 30 Jun 2025 22:29:01 GMT
• Title: Enhancing Interpretability in Generative Modeling: Statistically Disentangled Latent Spaces Guided by Generative Factors in Scientific Datasets
• Authors: Arkaprabha Ganguli, Nesar Ramachandra, Julie Bessac, Emil Constantinescu,
• Abstract summary: We introduce Aux-VAE, a novel architecture within the classical Variational Autoencoder framework.<n>We validate the efficacy of Aux-VAE through comparative assessments on multiple datasets, including astronomical simulations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction [62.376936772702905]
  Current deep learning architectures for remote sensing are fundamentally rigid.<n>We introduce the Spatial-Temporal-Spectral Unified Network (STSUN) for unified modeling.<n> STSUN can adapt to input and output data with arbitrary spatial sizes, temporal lengths, and spectral bands.<n>It unifies disparate dense prediction tasks within a single architecture by conditioning the model on trainable task embeddings.
  arXiv  Detail & Related papers  (2025-05-18T07:39:17Z)
• Learning a Single Index Model from Anisotropic Data with vanilla Stochastic Gradient Descent [7.8378818005171125]
  We investigate the problem of learning a Single Index Model (SIM) for studying the ability of neural networks to learn features.<n>In this study, we analyze the learning dynamics of vanilla Gradient Descent (SGD) under the SIM with anisotropic input data.<n>We derive upper and lower bounds on the sample complexity using a notion of effective dimension that is determined by the structure of the covariance matrix.
  arXiv  Detail & Related papers  (2025-03-31T01:07:30Z)
• Data Augmentation with Variational Autoencoder for Imbalanced Dataset [1.2289361708127877]
  Learning from an imbalanced distribution presents a major challenge in predictive modeling.<n>We develop a novel approach for generating data, combining VAE with a smoothed bootstrap, specifically designed to address the challenges of IR.
  arXiv  Detail & Related papers  (2024-12-09T22:59:03Z)
• The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness [50.52507648690234]
  Federated learning has the risk of skewing fine-tuning features and compromising the robustness of the model. We introduce three robustness indicators and conduct experiments across diverse robust datasets. Our approach markedly enhances the robustness across diverse scenarios, encompassing various parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-01-25T09:18:51Z)
• Joint Distributional Learning via Cramer-Wold Distance [0.7614628596146602]
  We introduce the Cramer-Wold distance regularization, which can be computed in a closed-form, to facilitate joint distributional learning for high-dimensional datasets. We also introduce a two-step learning method to enable flexible prior modeling and improve the alignment between the aggregated posterior and the prior distribution.
  arXiv  Detail & Related papers  (2023-10-25T05:24:23Z)
• Disentanglement via Latent Quantization [60.37109712033694]
  In this work, we construct an inductive bias towards encoding to and decoding from an organized latent space. We demonstrate the broad applicability of this approach by adding it to both basic data-re (vanilla autoencoder) and latent-reconstructing (InfoGAN) generative models.
  arXiv  Detail & Related papers  (2023-05-28T06:30:29Z)
• VTAE: Variational Transformer Autoencoder with Manifolds Learning [144.0546653941249]
  Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables. The nonlinearity of the generator implies that the latent space shows an unsatisfactory projection of the data space, which results in poor representation learning. We show that geodesics and accurate computation can substantially improve the performance of deep generative models.
  arXiv  Detail & Related papers  (2023-04-03T13:13:19Z)
• Variational Autoencoding Neural Operators [17.812064311297117]
  Unsupervised learning with functional data is an emerging paradigm of machine learning research with applications to computer vision, climate modeling and physical systems. We present Variational Autoencoding Neural Operators (VANO), a general strategy for making a large class of operator learning architectures act as variational autoencoders.
  arXiv  Detail & Related papers  (2023-02-20T22:34:43Z)
• Learning from few examples with nonlinear feature maps [68.8204255655161]
  We explore the phenomenon and reveal key relationships between dimensionality of AI model's feature space, non-degeneracy of data distributions, and the model's generalisation capabilities. The main thrust of our present analysis is on the influence of nonlinear feature transformations mapping original data into higher- and possibly infinite-dimensional spaces on the resulting model's generalisation capabilities.
  arXiv  Detail & Related papers  (2022-03-31T10:36:50Z)
• Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations [68.62843292346813]
  We propose a structured latent ODE model that captures system input variations within its latent representation. Building on a static variable specification, our model learns factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space.
  arXiv  Detail & Related papers  (2022-02-25T20:00:56Z)
• Is Disentanglement enough? On Latent Representations for Controllable Music Generation [78.8942067357231]
  In the absence of a strong generative decoder, disentanglement does not necessarily imply controllability. The structure of the latent space with respect to the VAE-decoder plays an important role in boosting the ability of a generative model to manipulate different attributes.
  arXiv  Detail & Related papers  (2021-08-01T18:37:43Z)
• Neural Decomposition: Functional ANOVA with Variational Autoencoders [9.51828574518325]
  Variational Autoencoders (VAEs) have become a popular approach for dimensionality reduction. Due to the black-box nature of VAEs, their utility for healthcare and genomics applications has been limited. We focus on characterising the sources of variation in Conditional VAEs.
  arXiv  Detail & Related papers  (2020-06-25T10:29:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.