CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation

• URL: http://arxiv.org/abs/2607.08254v1
• Date: Thu, 09 Jul 2026 08:58:44 GMT
• Title: CASL-VAE: Learning Structured Latent Variables from Unpaired Data for Semi-supervised Clustering and Paired Sample Generation
• Abstract summary: Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems.<n>We propose textitCASL-VAE, a deep contrastive latent variable model that learns structured latent generative factors from unpaired data.
• Score: 16.737784124258898
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Quantifying variability in a target population relative to a reference population is central to many scientific and clinical problems (e.g., diseased vs. healthy). Yet, without paired data and in the presence of heterogeneous target variation, existing methods struggle to separate multiple modes of target-specific variation. We propose \textit{CASL-VAE}, a deep contrastive latent variable model that learns structured latent generative factors from unpaired data. CASL-VAE factorizes variation into continuous common latent factors shared across populations and hierarchical salient latent factors that model target-specific heterogeneity as discrete subtypes and continuous within-subtype variation. Using variational inference, we show how approximate joint likelihood optimization over reference and target domains can be performed using unpaired data, providing a principled basis for paired-sample generation and cross-domain analysis. We validate CASL-VAE on semi-synthetic neuroimaging data, demonstrating improved subtype recovery and paired-sample generation compared to baseline clustering and generative models. We also validate its ability to reveal biologically plausible heterogeneity in Alzheimer's disease.

Related papers

• Unlasting: Unpaired Single-Cell Multi-Perturbation Estimation by Dual Conditional Diffusion Implicit Bridges [68.98973318553983]
  We propose a framework based on Dual Diffusion Implicit Bridges (DDIB) to learn the mapping between different data distributions.<n>We integrate gene regulatory network (GRN) information to propagate perturbation signals in a biologically meaningful way.<n>We also incorporate a masking mechanism to predict silent genes, improving the quality of generated profiles.
  arXiv  Detail & Related papers  (2025-06-26T09:05:38Z)
• Learning Divergence Fields for Shift-Robust Graph Representations [73.11818515795761]
  In this work, we propose a geometric diffusion model with learnable divergence fields for the challenging problem with interdependent data. We derive a new learning objective through causal inference, which can guide the model to learn generalizable patterns of interdependence that are insensitive across domains.
  arXiv  Detail & Related papers  (2024-06-07T14:29:21Z)
• Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models [83.02797560769285]
  Data-Free Meta-Learning (DFML) aims to derive knowledge from a collection of pre-trained models without accessing their original data.<n>Current methods often overlook the heterogeneity among pre-trained models, which leads to performance degradation due to task conflicts.
  arXiv  Detail & Related papers  (2024-05-26T13:11:55Z)
• Combining propensity score methods with variational autoencoders for generating synthetic data in presence of latent sub-groups [0.0]
  Heterogeneity might be known, e.g., as indicated by sub-groups labels, or might be unknown and reflected only in properties of distributions, such as bimodality or skewness. We investigate how such heterogeneity can be preserved and controlled when obtaining synthetic data from variational autoencoders (VAEs), i.e., a generative deep learning technique.
  arXiv  Detail & Related papers  (2023-12-12T22:49:24Z)
• Identifiable Latent Polynomial Causal Models Through the Lens of Change [82.14087963690561]
  Causal representation learning aims to unveil latent high-level causal representations from observed low-level data.<n>One of its primary tasks is to provide reliable assurance of identifying these latent causal models, known as identifiability.
  arXiv  Detail & Related papers  (2023-10-24T07:46:10Z)
• Conditionally Invariant Representation Learning for Disentangling Cellular Heterogeneity [25.488181126364186]
  This paper presents a novel approach that leverages domain variability to learn representations that are conditionally invariant to unwanted variability or distractors. We apply our method to grand biological challenges, such as data integration in single-cell genomics. Specifically, the proposed approach helps to disentangle biological signals from data biases that are unrelated to the target task or the causal explanation of interest.
  arXiv  Detail & Related papers  (2023-07-02T12:52:41Z)
• Gaussian Latent Dirichlet Allocation for Discrete Human State Discovery [1.057079240576682]
  We propose and validate an unsupervised probabilistic model, Gaussian Latent Dirichlet Allocation (GLDA), for the problem of discrete state discovery. GLDA borrows the individual-specific mixture structure from a popular topic model Latent Dirichlet Allocation (LDA) in Natural Language Processing. We found that in both datasets the GLDA-learned class weights achieved significantly higher correlations with clinically assessed depression, anxiety, and stress scores than those produced by the baseline GMM.
  arXiv  Detail & Related papers  (2022-06-28T18:33:46Z)
• Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets [53.34152466646884]
  In this paper, we show how bringing recent results on equivariant representation learning instantiated on structured spaces together with simple use of classical results on causal inference provides an effective practical solution. We demonstrate how our model allows dealing with more than one nuisance variable under some assumptions and can enable analysis of pooled scientific datasets in scenarios that would otherwise entail removing a large portion of the samples.
  arXiv  Detail & Related papers  (2022-03-29T04:54:06Z)
• Accounting for Unobserved Confounding in Domain Generalization [107.0464488046289]
  This paper investigates the problem of learning robust, generalizable prediction models from a combination of datasets. Part of the challenge of learning robust models lies in the influence of unobserved confounders. We demonstrate the empirical performance of our approach on healthcare data from different modalities.
  arXiv  Detail & Related papers  (2020-07-21T08:18:06Z)
• NestedVAE: Isolating Common Factors via Weak Supervision [45.366986365879505]
  We identify the connection between the task of bias reduction and that of isolating factors common between domains. To isolate the common factors we combine the theory of deep latent variable models with information bottleneck theory. Two outer VAEs with shared weights attempt to reconstruct the input and infer a latent space, whilst a nested VAE attempts to reconstruct the latent representation of one image, from the latent representation of its paired image.
  arXiv  Detail & Related papers  (2020-02-26T15:49:57Z)
• Blocked Clusterwise Regression [0.0]
  We generalize previous approaches to discrete unobserved heterogeneity by allowing each unit to have multiple latent variables. We contribute to the theory of clustering with an over-specified number of clusters and derive new convergence rates for this setting.
  arXiv  Detail & Related papers  (2020-01-29T23:29:31Z)

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.