# Disentangled Representation Learning with Wasserstein Total Correlation

arXiv: https://arxiv.org/abs/1912.12818 · HTML: https://mlsanity.com/paper/1912.12818/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Dec 2019.

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

- [Desiderata for Representation Learning: A Causal Perspective](https://mlsanity.com/paper/2109.03795/) (2021)
- [Multimodal Variational Auto-encoder based Audio-Visual Segmentation](https://mlsanity.com/paper/2310.08303/) (2023)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Statistical Inference for Optimal Transport Maps: Recent Advances and Perspectives](https://mlsanity.com/paper/2506.19025/) (2025)

## Abstract (arXiv)

Unsupervised learning of disentangled representations involves uncovering of different factors of variations that contribute to the data generation process. Total correlation penalization has been a key component in recent methods towards disentanglement. However, Kullback-Leibler (KL) divergence-based total correlation is metric-agnostic and sensitive to data samples. In this paper, we introduce Wasserstein total correlation in both variational autoencoder and Wasserstein autoencoder settings to learn disentangled latent representations. A critic is adversarially trained along with the main objective to estimate the Wasserstein total correlation term. We discuss the benefits of using Wasserstein distance over KL divergence to measure independence and conduct quantitative and qualitative experiments on several data sets. Moreover, we introduce a new metric to measure disentanglement. We show that the proposed approach has comparable performances on disentanglement with smaller sacrifices in reconstruction abilities.