# InfoCatVAE: Representation Learning with Categorical Variational Autoencoders

arXiv: https://arxiv.org/abs/1806.08240 · HTML: https://mlsanity.com/paper/1806.08240/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2018.

## Built on by (most cited first, 5 of 5)

- [Manifold Learning by Mixture Models of VAEs for Inverse Problems](https://mlsanity.com/paper/2303.15244/) (2023)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [Atlas Generative Models and Geodesic Interpolation](https://mlsanity.com/paper/2102.00264/) (2021)
- [Correcting Flaws in Common Disentanglement Metrics](https://mlsanity.com/paper/2304.02335/) (2023)
- [Estimating Dataset Dimension via Singular Metrics under the Manifold Hypothesis: Application to Inverse Problems](https://mlsanity.com/paper/2507.07291/) (2025)

## Abstract (arXiv)

This paper describes InfoCatVAE, an extension of the variational autoencoder that enables unsupervised disentangled representation learning. InfoCatVAE uses multimodal distributions for the prior and the inference network and then maximizes the evidence lower bound objective (ELBO). We connect the new ELBO derived for our model with a natural soft clustering objective which explains the robustness of our approach. We then adapt the InfoGANs method to our setting in order to maximize the mutual information between the categorical code and the generated inputs and obtain an improved model.