mlsanityData to 14 Oct 2026

Variational Learning of Disentangled Representations

arXiv 2506.17182 ↗First posted 20 Jun 2025cs.LG stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

Disentangled representations separate factors that are shared across conditions from those that are condition-specific. Such separation is needed for generalization to new domains, treatments, patients, or species. A dominant line of work pursues this goal through variational formulations. While these approaches achieve partial disentanglement, they often exhibit three common limitations: they either do not remove all condition-specific information from the condition-specific representation, allow the condition-specific representation to become uninformative, or impose independence assumptions that do not reflect the underlying generative process. In this work, we introduce DisCoVR, a variational framework that addresses these limitations. Its objective is aligned with the probabilistic structure of the data-generating process, and includes an adversarial term that prevents condition-specific information from being encoded in the condition-specific representation.DisCoVR reconstructs the data from both shared and condition-specific representations, ensuring that each remains informative, and uses a structured prior that further reinforces the informativeness of both representations. We show that across synthetic, image, and single-cell RNA-sequencing datasets, DisCoVR achieves stronger disentanglement compared to previous approaches.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 46 of its 78 references that are in the map. First posted on arXiv 20 Jun 2025.

Builds on

46 of 78 references.

References · 46

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  3. 2022Generative Adversarial Networkscited by 5,627
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  5. 2019Invariant Risk Minimizationcited by 1,854
  6. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,200
  7. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 742
  8. 2018MINE: Mutual Information Neural Estimationcited by 683
  9. 2013Domain Generalization via Invariant Feature Representationcited by 623
  10. 2017Learning multiple visual domains with residual adapterscited by 557
  11. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  12. 2021Just Train Twice: Improving Group Robustness without Training Group Informationcited by 523
34 more
  1. 2015Deep Metric Learning via Lifted Structured Feature Embeddingcited by 449
  2. 2014Deep metric learning using Triplet networkcited by 422
  3. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  4. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 335
  5. 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 323
  6. 2017Sampling Matters in Deep Embedding Learningcited by 285
  7. 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
  8. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  9. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 183
  10. 2021Simple data balancing achieves competitive worst-group-accuracycited by 178
  11. 2018Efficient parametrization of multi-domain deep neural networkscited by 168
  12. 2020Domain Adaptive Ensemble Learningcited by 156
  13. 2018Domain Generalization via Conditional Invariant Representationcited by 146
  14. 2021On Calibration and Out-of-domain Generalizationcited by 134
  15. 2019Learning Robust Representations by Projecting Superficial Statistics Outcited by 123
  16. 2019DIVA: Domain Invariant Variational Autoencoderscited by 115
  17. 2018Best sources forward: domain generalization through source-specific netscited by 82
  18. 2018Learning Latent Subspaces in Variational Autoencoderscited by 51
  19. 2019Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalizationcited by 43
  20. 2019Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learningcited by 32
  21. 2020Capturing Label Characteristics in VAEscited by 30
  22. 2016Select-Additive Learning: Improving Generalization in Multimodal Sentiment Analysiscited by 29
  23. 2021Focus on the Common Good: Group Distributional Robustness Followscited by 25
  24. 2023Adversarial Bayesian Augmentation for Single-Source Domain Generalizationcited by 22
  25. 2023MADG: Margin-based Adversarial Learning for Domain Generalizationcited by 22
  26. 2022Localized Adversarial Domain Generalizationcited by 19
  27. 2014Two Modeling Strategies for Empirical Bayes Estimationcited by 16
  28. 2019Efficient Multi-Domain Network Learning by Covariance Normalizationcited by 16
  29. 2022Improving Diversity with Adversarially Learned Transformations for Domain Generalizationcited by 16
  30. 2023Distributionally Robust Post-hoc Classifiers under Prior Shiftscited by 16
  31. 2023Domain Generalization via Ensemble Stacking for Face Presentation Attack Detectioncited by 6
  32. 2023Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representationscited by 4
  33. 2022Model-agnostic Multi-Domain Learning with Domain-Specific Adapters for Action Recognitioncited by 3
  34. 2024Domain Adversarial Active Learning for Domain Generalization Classificationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Hybrid guided variational autoencoder for visual place recognitioncited by 0