# Disentangling and Learning Robust Representations with Natural Clustering

arXiv: https://arxiv.org/abs/1901.09415 · HTML: https://mlsanity.com/paper/1901.09415/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2019.

## Built on by (most cited first, 10 of 10)

- [Adapting the Linearised Laplace Model Evidence for Modern Deep Learning](https://mlsanity.com/paper/2206.08900/) (2022)
- [Sampling-based inference for large linear models, with application to linearised Laplace](https://mlsanity.com/paper/2210.04994/) (2022)
- [A Generative Model of Symmetry Transformations](https://mlsanity.com/paper/2403.01946/) (2024)
- [Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAE](https://mlsanity.com/paper/2102.00892/) (2021)
- [Bayesian Experimental Design for Computed Tomography with the Linearised Deep Image Prior](https://mlsanity.com/paper/2207.05714/) (2022)
- [Controllable Data Augmentation Through Deep Relighting](https://mlsanity.com/paper/2110.13996/) (2021)
- [Unsupervised Multiple Domain Translation through Controlled Disentanglement in Variational Autoencoder](https://mlsanity.com/paper/2401.09180/) (2024)
- [Break The Spell Of Total Correlation In betaTCVAE](https://mlsanity.com/paper/2210.08794/) (2022)
- [Image Reconstruction via Deep Image Prior Subspaces](https://mlsanity.com/paper/2302.10279/) (2023)
- [Rethinking Disentanglement under Dependent Factors of Variation](https://mlsanity.com/paper/2408.07016/) (2024)

## Abstract (arXiv)

Learning representations that disentangle the underlying factors of variability in data is an intuitive way to achieve generalization in deep models. In this work, we address the scenario where generative factors present a multimodal distribution due to the existence of class distinction in the data. We propose N-VAE, a model which is capable of separating factors of variation which are exclusive to certain classes from factors that are shared among classes. This model implements an explicitly compositional latent variable structure by defining a class-conditioned latent space and a shared latent space. We show its usefulness for detecting and disentangling class-dependent generative factors as well as its capacity to generate artificial samples which contain characteristics unseen in the training data.