# Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

arXiv: https://arxiv.org/abs/1811.04784 · HTML: https://mlsanity.com/paper/1811.04784/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2018.

## Built on by (most cited first, 28 of 28)

- [Abstraction and Analogy-Making in Artificial Intelligence](https://mlsanity.com/paper/2102.10717/) (2021)
- [Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Execution](https://mlsanity.com/paper/2103.14230/) (2021)
- [Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices](https://mlsanity.com/paper/2201.12382/) (2022)
- [Identifiability of Label Noise Transition Matrix](https://mlsanity.com/paper/2202.02016/) (2022)
- [A Review of Emerging Research Directions in Abstract Visual Reasoning](https://mlsanity.com/paper/2202.10284/) (2022)
- [Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning](https://mlsanity.com/paper/2111.12990/) (2021)
- [Symmetry-Based Representations for Artificial and Biological General Intelligence](https://mlsanity.com/paper/2203.09250/) (2022)
- [Dynamic Inference with Neural Interpreters](https://mlsanity.com/paper/2110.06399/) (2021)
- [Learning to reason over visual objects](https://mlsanity.com/paper/2303.02260/) (2023)
- [Selective Replay Enhances Learning in Online Continual Analogical Reasoning](https://mlsanity.com/paper/2103.03987/) (2021)
- [The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agents](https://mlsanity.com/paper/2107.05686/) (2021)
- [Slot Abstractors: Toward Scalable Abstract Visual Reasoning](https://mlsanity.com/paper/2403.03458/) (2024)
- [Raven's Progressive Matrices Completion with Latent Gaussian Process Priors](https://mlsanity.com/paper/2103.12045/) (2021)
- [Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems](https://mlsanity.com/paper/2307.07734/) (2023)
- [On the relationship between disentanglement and multi-task learning](https://mlsanity.com/paper/2110.03498/) (2021)
- [Symmetry and Complexity in Object-Centric Deep Active Inference Models](https://mlsanity.com/paper/2304.14493/) (2023)
- [Compositional Law Parsing with Latent Random Functions](https://mlsanity.com/paper/2209.09115/) (2022)
- [Unraveling the geometry of visual relational reasoning](https://mlsanity.com/paper/2502.17382/) (2025)
- [Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introduction](https://mlsanity.com/paper/2302.04238/) (2023)
- [Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection](https://mlsanity.com/paper/2401.09966/) (2024)
- [DAReN: A Collaborative Approach Towards Reasoning And Disentangling](https://mlsanity.com/paper/2109.13156/) (2021)
- [Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning](https://mlsanity.com/paper/2403.00352/) (2024)
- [Transferring disentangled representations: bridging the gap between synthetic and real images](https://mlsanity.com/paper/2409.18017/) (2024)
- [Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Tasks](https://mlsanity.com/paper/2302.07137/) (2023)
- [ETHER: Aligning Emergent Communication for Hindsight Experience Replay](https://mlsanity.com/paper/2307.15494/) (2023)
- [A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoning](https://mlsanity.com/paper/2403.05641/) (2024)
- [XFACTORS: Disentangled Information Bottleneck via Contrastive Supervision](https://mlsanity.com/paper/2601.21688/) (2026)
- [Pretraining Curricula Enable Selective Fine-tuning](https://mlsanity.com/paper/2607.04846/) (2026)

## Abstract (arXiv)

In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive Matrices. We show that the latent representations, learned by unsupervised training using the right objective function, significantly outperform the same architectures trained with purely supervised learning, especially when it comes to generalization.