# Learning Disentangled Joint Continuous and Discrete Representations

arXiv: https://arxiv.org/abs/1804.00104 · HTML: https://mlsanity.com/paper/1804.00104/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2018.

## Built on by (most cited first, 30 of 83)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [A Review of the Gumbel-max Trick and its Extensions for Discrete Stochasticity in Machine Learning](https://mlsanity.com/paper/2110.01515/) (2021)
- [Multi-VAE: Learning Disentangled View-common and View-peculiar Visual Representations for Multi-view Clustering](https://mlsanity.com/paper/2106.11232/) (2021)
- [Discover the Unknown Biased Attribute of an Image Classifier](https://mlsanity.com/paper/2104.14556/) (2021)
- [Disentangling Hate in Online Memes](https://mlsanity.com/paper/2108.06207/) (2021)
- [Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation](https://mlsanity.com/paper/2108.07668/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Commutative Lie Group VAE for Disentanglement Learning](https://mlsanity.com/paper/2106.03375/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Disentangled Recurrent Wasserstein Autoencoder](https://mlsanity.com/paper/2101.07496/) (2021)
- [SKID RAW: Skill Discovery from Raw Trajectories](https://mlsanity.com/paper/2103.14610/) (2021)
- [CNeRV: Content-adaptive Neural Representation for Visual Data](https://mlsanity.com/paper/2211.10421/) (2022)
- [Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Information](https://mlsanity.com/paper/2103.07084/) (2021)
- [Disentangling Generative Factors in Natural Language with Discrete Variational Autoencoders](https://mlsanity.com/paper/2109.07169/) (2021)
- [Latent Traversals in Generative Models as Potential Flows](https://mlsanity.com/paper/2304.12944/) (2023)
- [Motion Planning by Learning the Solution Manifold in Trajectory Optimization](https://mlsanity.com/paper/2107.05842/) (2021)
- [Learning Disentangled Representations of Negation and Uncertainty](https://mlsanity.com/paper/2204.00511/) (2022)
- [Benchmarks, Algorithms, and Metrics for Hierarchical Disentanglement](https://mlsanity.com/paper/2102.05185/) (2021)
- [Learning Disentangled Representations for Natural Language Definitions](https://mlsanity.com/paper/2210.02898/) (2022)
- [Flow Factorized Representation Learning](https://mlsanity.com/paper/2309.13167/) (2023)
- [Lifelong Mixture of Variational Autoencoders](https://mlsanity.com/paper/2107.04694/) (2021)
- [Raven's Progressive Matrices Completion with Latent Gaussian Process Priors](https://mlsanity.com/paper/2103.12045/) (2021)
- [Disentanglement Analysis with Partial Information Decomposition](https://mlsanity.com/paper/2108.13753/) (2021)
- [Closed-Loop Unsupervised Representation Disentanglement with β-VAE Distillation and Diffusion Probabilistic Feedback](https://mlsanity.com/paper/2402.02346/) (2024)
- [Unsupervised Learning of Neurosymbolic Encoders](https://mlsanity.com/paper/2107.13132/) (2021)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood](https://mlsanity.com/paper/2107.04705/) (2021)
- [Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps](https://mlsanity.com/paper/2110.06983/) (2021)
- [Transductive Decoupled Variational Inference for Few-Shot Classification](https://mlsanity.com/paper/2208.10559/) (2022)

## 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.