# On the Transfer of Disentangled Representations in Realistic Settings

arXiv: https://arxiv.org/abs/2010.14407 · HTML: https://mlsanity.com/paper/2010.14407/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Oct 2020.

## Built on by (most cited first, 30 of 63)

- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Contrastive Learning Inverts the Data Generating Process](https://mlsanity.com/paper/2102.08850/) (2021)
- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [A Fine-Grained Analysis on Distribution Shift](https://mlsanity.com/paper/2110.11328/) (2021)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Entropy is not Enough for Test-Time Adaptation: From the Perspective of Disentangled Factors](https://mlsanity.com/paper/2403.07366/) (2024)
- [Out-Of-Distribution Generalization on Graphs: A Survey](https://mlsanity.com/paper/2202.07987/) (2022)
- [Towards Principled Disentanglement for Domain Generalization](https://mlsanity.com/paper/2111.13839/) (2021)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Weakly Supervised Representation Learning with Sparse Perturbations](https://mlsanity.com/paper/2206.01101/) (2022)
- [Visual Representation Learning Does Not Generalize Strongly Within the Same Domain](https://mlsanity.com/paper/2107.08221/) (2021)
- [Identifiable Deep Generative Models via Sparse Decoding](https://mlsanity.com/paper/2110.10804/) (2021)
- [Mechanistic Mode Connectivity](https://mlsanity.com/paper/2211.08422/) (2022)
- [Learning Disentangled Representations in the Imaging Domain](https://mlsanity.com/paper/2108.12043/) (2021)
- [Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning](https://mlsanity.com/paper/2211.14666/) (2022)
- [Compositional Generalization in Unsupervised Compositional Representation Learning: A Study on Disentanglement and Emergent Language](https://mlsanity.com/paper/2210.00482/) (2022)
- [Robust and Efficient Medical Imaging with Self-Supervision](https://mlsanity.com/paper/2205.09723/) (2022)
- [Disentanglement of Correlated Factors via Hausdorff Factorized Support](https://mlsanity.com/paper/2210.07347/) (2022)
- [Sparse Interventions in Language Models with Differentiable Masking](https://mlsanity.com/paper/2112.06837/) (2021)
- [Leveraging sparse and shared feature activations for disentangled representation learning](https://mlsanity.com/paper/2304.07939/) (2023)
- [On Causally Disentangled Representations](https://mlsanity.com/paper/2112.05746/) (2021)
- [Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning](https://mlsanity.com/paper/2301.05169/) (2023)
- [Discrete Key-Value Bottleneck](https://mlsanity.com/paper/2207.11240/) (2022)
- [Pretraining in Deep Reinforcement Learning: A Survey](https://mlsanity.com/paper/2211.03959/) (2022)
- [Domain Generalisation via Risk Distribution Matching](https://mlsanity.com/paper/2310.18598/) (2023)
- [Identifiable Contrastive Learning with Automatic Feature Importance Discovery](https://mlsanity.com/paper/2310.18904/) (2023)
- [Inductive Biases for Object-Centric Representations in the Presence of Complex Textures](https://mlsanity.com/paper/2204.08479/) (2022)
- [Does Data Scaling Lead to Visual Compositional Generalization?](https://mlsanity.com/paper/2507.07102/) (2025)
- [The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents](https://mlsanity.com/paper/2107.05686/) (2021)
- [Exploring the Latent Space of Autoencoders with Interventional Assays](https://mlsanity.com/paper/2106.16091/) (2021)

## Abstract (arXiv)

Learning meaningful representations that disentangle the underlying structure of the data generating process is considered to be of key importance in machine learning. While disentangled representations were found to be useful for diverse tasks such as abstract reasoning and fair classification, their scalability and real-world impact remain questionable. We introduce a new high-resolution dataset with 1M simulated images and over 1,800 annotated real-world images of the same setup. In contrast to previous work, this new dataset exhibits correlations, a complex underlying structure, and allows to evaluate transfer to unseen simulated and real-world settings where the encoder i) remains in distribution or ii) is out of distribution. We propose new architectures in order to scale disentangled representation learning to realistic high-resolution settings and conduct a large-scale empirical study of disentangled representations on this dataset. We observe that disentanglement is a good predictor for out-of-distribution (OOD) task performance.