# A Two-Step Disentanglement Method

arXiv: https://arxiv.org/abs/1709.00199 · HTML: https://mlsanity.com/paper/1709.00199/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Sep 2017.

## Built on by (most cited first, 13 of 13)

- [Understanding Object Dynamics for Interactive Image-to-Video Synthesis](https://mlsanity.com/paper/2106.11303/) (2021)
- [Algorithm Fairness in AI for Medicine and Healthcare](https://mlsanity.com/paper/2110.00603/) (2021)
- [A Survey of Methods, Challenges and Perspectives in Causality](https://mlsanity.com/paper/2302.00293/) (2023)
- [Disentangled Representation Learning with Transmitted Information Bottleneck](https://mlsanity.com/paper/2311.01686/) (2023)
- [Improving ClusterGAN Using Self-Augmented Information Maximization of Disentangling Latent Spaces](https://mlsanity.com/paper/2107.12706/) (2021)
- [Adversarial Disentanglement by Backpropagation with Physics-Informed Variational Autoencoder](https://mlsanity.com/paper/2506.13658/) (2025)
- [Counterfactual Explanation for Regression via Disentanglement in Latent Space](https://mlsanity.com/paper/2311.08228/) (2023)
- [Self-supervised Latent Space Optimization with Nebula Variational Coding](https://mlsanity.com/paper/2506.01414/) (2025)
- [On Disentangled and Locally Fair Representations](https://mlsanity.com/paper/2205.02673/) (2022)
- [3DLatNav: Navigating Generative Latent Spaces for Semantic-Aware 3D Object Manipulation](https://mlsanity.com/paper/2211.09770/) (2022)
- [Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space](https://mlsanity.com/paper/2307.13390/) (2023)
- [LCIP: Loss-Controlled Inverse Projection of High-Dimensional Image Data](https://mlsanity.com/paper/2602.11141/) (2026)
- [The Trade-off Between Covariate Dependence and Latent Structure in Representation Learning](https://mlsanity.com/paper/2608.16245/) (2026)

## Abstract (arXiv)

We address the problem of disentanglement of factors that generate a given data into those that are correlated with the labeling and those that are not. Our solution is simpler than previous solutions and employs adversarial training. First, the part of the data that is correlated with the labels is extracted by training a classifier. Then, the other part is extracted such that it enables the reconstruction of the original data but does not contain label information. The utility of the new method is demonstrated on visual datasets as well as on financial data. Our code is available at https://github.com/naamahadad/A-Two-Step-Disentanglement-Method