# Are Disentangled Representations Helpful for Abstract Visual Reasoning?

arXiv: https://arxiv.org/abs/1905.12506 · HTML: https://mlsanity.com/paper/1905.12506/

## Key facts

- Cited by 100 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 May 2019.

## Built on by (most cited first, 30 of 100)

- [Towards Causal Representation Learning](https://mlsanity.com/paper/2102.11107/) (2021)
- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [GlanceNets: Interpretabile, Leak-proof Concept-based Models](https://mlsanity.com/paper/2205.15612/) (2022)
- [Compositional Generalization from First Principles](https://mlsanity.com/paper/2307.05596/) (2023)
- [Mechanistic Mode Connectivity](https://mlsanity.com/paper/2211.08422/) (2022)
- [Self-Supervised Learning Disentangled Group Representation as Feature](https://mlsanity.com/paper/2110.15255/) (2021)
- [Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning](https://mlsanity.com/paper/2211.14666/) (2022)
- [CDPAM: Contrastive learning for perceptual audio similarity](https://mlsanity.com/paper/2102.05109/) (2021)
- [A Novel Estimator of Mutual Information for Learning to Disentangle Textual Representations](https://mlsanity.com/paper/2105.02685/) (2021)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space](https://mlsanity.com/paper/2406.19370/) (2024)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)
- [An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild](https://mlsanity.com/paper/2106.15610/) (2021)
- [Where and What? Examining Interpretable Disentangled Representations](https://mlsanity.com/paper/2104.05622/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Learned feature representations are biased by complexity, learning order, position, and more](https://mlsanity.com/paper/2405.05847/) (2024)
- [Towards Building A Group-based Unsupervised Representation Disentanglement Framework](https://mlsanity.com/paper/2102.10303/) (2021)
- [Causal Triplet: An Open Challenge for Intervention-centric Causal Representation Learning](https://mlsanity.com/paper/2301.05169/) (2023)
- [Learning Robust Representation for Joint Grading of Ophthalmic Diseases via Adaptive Curriculum and Feature Disentanglement](https://mlsanity.com/paper/2207.04183/) (2022)
- [When does compositional structure yield compositional generalization? A kernel theory](https://mlsanity.com/paper/2405.16391/) (2024)
- [Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning](https://mlsanity.com/paper/2502.12425/) (2025)
- [Learning to reason over visual objects](https://mlsanity.com/paper/2303.02260/) (2023)
- [Drop, Swap, and Generate: A Self-Supervised Approach for Generating Neural Activity](https://mlsanity.com/paper/2111.02338/) (2021)
- [Scaling-up Disentanglement for Image Translation](https://mlsanity.com/paper/2103.14017/) (2021)
- [A Contrastive Objective for Learning Disentangled Representations](https://mlsanity.com/paper/2203.11284/) (2022)
- [Disentangled Representations from Non-Disentangled Models](https://mlsanity.com/paper/2102.06204/) (2021)
- [Inductive Biases for Object-Centric Representations in the Presence of Complex Textures](https://mlsanity.com/paper/2204.08479/) (2022)

## Abstract (arXiv)

A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is useful in learning to solve many real-world down-stream tasks, there is little empirical evidence that supports this claim. In this paper, we conduct a large-scale study that investigates whether disentangled representations are more suitable for abstract reasoning tasks. Using two new tasks similar to Raven's Progressive Matrices, we evaluate the usefulness of the representations learned by 360 state-of-the-art unsupervised disentanglement models. Based on these representations, we train 3600 abstract reasoning models and observe that disentangled representations do in fact lead to better down-stream performance. In particular, they enable quicker learning using fewer samples.