# A Commentary on the Unsupervised Learning of Disentangled Representations

arXiv: https://arxiv.org/abs/2007.14184 · HTML: https://mlsanity.com/paper/2007.14184/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2020.

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

- [Comparing the latent space of generative models](https://mlsanity.com/paper/2207.06812/) (2022)
- [Separating common from salient patterns with Contrastive Representation Learning](https://mlsanity.com/paper/2402.11928/) (2024)
- [From latent dynamics to meaningful representations](https://mlsanity.com/paper/2209.00905/) (2022)
- [Distortion-Disentangled Contrastive Learning](https://mlsanity.com/paper/2303.05066/) (2023)
- [Synergy Between Sufficient Changes and Sparse Mixing Procedure for Disentangled Representation Learning](https://mlsanity.com/paper/2503.00639/) (2025)
- [Video Reenactment as Inductive Bias for Content-Motion Disentanglement](https://mlsanity.com/paper/2102.00324/) (2021)
- [Concept-free Causal Disentanglement with Variational Graph Auto-Encoder](https://mlsanity.com/paper/2311.10638/) (2023)
- [Linear causal disentanglement via higher-order cumulants](https://mlsanity.com/paper/2407.04605/) (2024)
- [CLEAR: Unlearning Spurious Style-Content Associations with Contrastive LEarning with Anti-contrastive Regularization](https://mlsanity.com/paper/2507.18794/) (2025)
- [Causal Graph Neural Networks for Healthcare](https://mlsanity.com/paper/2511.02531/) (2025)
- [Skimming and Scanning for Untrimmed Video Action Recognition](https://mlsanity.com/paper/2104.10492/) (2021)
- [Disentangled Interest Network for Out-of-Distribution CTR Prediction](https://mlsanity.com/paper/2602.00002/) (2025)
- [Posterior-Calibrated Causal Circuits in Variational Autoencoders: Why Image-Domain Interpretability Fails on Tabular Data](https://mlsanity.com/paper/2603.21236/) (2026)

## Abstract (arXiv)

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In this paper, we summarize the results of Locatello et al., 2019, and focus on their implications for practitioners. We discuss the theoretical result showing that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases and the practical challenges it entails. Finally, we comment on our experimental findings, highlighting the limitations of state-of-the-art approaches and directions for future research.