mlsanityData to 7 Oct 2026

Learning Disentangled Joint Continuous and Discrete Representations

arXiv 1804.00104 ↗First posted 31 Mar 2018stat.ML cs.LGcited by 83

Not on the map. Why?

Abstract (arXiv)

We present a framework for learning disentangled and interpretable jointly continuous and discrete representations in an unsupervised manner. By augmenting the continuous latent distribution of variational autoencoders with a relaxed discrete distribution and controlling the amount of information encoded in each latent unit, we show how continuous and categorical factors of variation can be discovered automatically from data. Experiments show that the framework disentangles continuous and discrete generative factors on various datasets and outperforms current disentangling methods when a discrete generative factor is prominent.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 18; 2023: 12; 2024: 9; 2025: 8; 2026: 6.

83 papers.

Sort:

By area:

  1. 2022Disentangled Representation Learningcited by 111
  2. 2022Tutorial on amortized optimizationcited by 83
  3. 2021A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learningcited by 82
  4. 2021Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clusteringcited by 51
  5. 2021Discover the Unknown Biased Attribute of an Image Classifiercited by 46
  6. 2021Disentangling Hate in Online Memescited by 46
  7. 2021Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generationcited by 35
  8. 2021Where and What? Examining Interpretable Disentangled Representationscited by 27
  9. 2021Commutative Lie Group VAE for Disentanglement Learningcited by 27
  10. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  11. 2021Disentangled Recurrent Wasserstein Autoencodercited by 22
  12. 2021SKID RAW: Skill Discovery from Raw Trajectoriescited by 22
38 more
  1. 2022CNeRV: Content-adaptive Neural Representation for Visual Datacited by 21
  2. 2021Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoderscited by 19
  3. 2021Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Informationcited by 18
  4. 2023Latent Traversals in Generative Models as Potential Flowscited by 17
  5. 2021Motion Planning by Learning the Solution Manifold in Trajectory Optimizationcited by 13
  6. 2022Learning Disentangled Representations of Negation and Uncertaintycited by 13
  7. 2021Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglementcited by 12
  8. 2022Learning Disentangled Representations for Natural Language Definitionscited by 12
  9. 2023Flow Factorized Representation Learningcited by 11
  10. 2021Lifelong Mixture of Variational Autoencoderscited by 10
  11. 2021Raven's Progressive Matrices Completion with Latent Gaussian Process Priorscited by 9
  12. 2021Disentanglement Analysis with Partial Information Decompositioncited by 9
  13. 2024Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedbackcited by 9
  14. 2021Unsupervised Learning of Neurosymbolic Encoderscited by 8
  15. 2021Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAEcited by 7
  16. 2021InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihoodcited by 7
  17. 2021Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Mapscited by 7
  18. 2022Transductive Decoupled Variational Inference for Few-Shot Classificationcited by 7
  19. 2023Causal Disentangled Variational Auto-Encoder for Preference Understanding in Recommendationcited by 7
  20. 2023Multi-Agent Reinforcement Learning Based on Representational Communication for Large-Scale Traffic Signal Controlcited by 7
  21. 2024Rethinking Multi-view Representation Learning via Distilled Disentanglingcited by 5
  22. 2022Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variationcited by 4
  23. 2025Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Modelscited by 4
  24. 2021Variational Nested Dropoutcited by 3
  25. 2021Hyperbolic Disentangled Representation for Fine-Grained Aspect Extractioncited by 3
  26. 2021Improving Robot Localisation by Ignoring Visual Distractioncited by 2
  27. 2021Improving ClusterGAN Using Self-Augmented Information Maximization of Disentangling Latent Spacescited by 2
  28. 2022DIDER: Discovering Interpretable Dynamically Evolving Relationscited by 2
  29. 2023Causally Disentangled Generative Variational AutoEncodercited by 2
  30. 2023Position Paper on Materials Design -- A Modern Approachcited by 2
  31. 2024Unsupervised Representation Learning from Sparse Transformation Analysiscited by 2
  32. 2025Negative Binomial Variational Autoencoders for Overdispersed Latent Modelingcited by 2
  33. 2021Disentangled Sequence Clustering for Human Intention Inferencecited by 1
  34. 2021DEFT: Distilling Entangled Factors by Preventing Information Diffusioncited by 1
  35. 2021Group-disentangled Representation Learning with Weakly-Supervised Regularizationcited by 1
  36. 2021Self-supervised Enhancement of Latent Discovery in GANscited by 1
  37. 2022ReCAB-VAE: Gumbel-Softmax Variational Inference Based on Analytic Divergencecited by 1
  38. 2022Invisible-to-Visible: Privacy-Aware Human Segmentation using Airborne Ultrasound via Collaborative Learning Probabilistic U-Netcited by 1

50 most cited of 83 All 83 (JSON)