mlsanityData to 7 Oct 2026

Improving Generalization for Abstract Reasoning Tasks Using Disentangled Feature Representations

arXiv 1811.04784 ↗First posted 12 Nov 2018cs.LG cs.NE stat.MLcited by 28

Not on the map. Why?

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.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 5; 2023: 6; 2024: 5; 2025: 1; 2026: 2.

28 papers.

Sort:

By area:

  1. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  2. 2021Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Executioncited by 43
  3. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  4. 2022Identifiability of Label Noise Transition Matrixcited by 34
  5. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  6. 2021Learning Algebraic Representation for Systematic Generalization in Abstract Reasoningcited by 27
  7. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  8. 2021Dynamic Inference with Neural Interpreterscited by 24
  9. 2023Learning to reason over visual objectscited by 19
  10. 2021Selective Replay Enhances Learning in Online Continual Analogical Reasoningcited by 12
  11. 2021The Role of Pretrained Representations for the OOD Generalization of Reinforcement Learning Agentscited by 12
  12. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
16 more
  1. 2021Raven's Progressive Matrices Completion with Latent Gaussian Process Priorscited by 9
  2. 2023Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problemscited by 6
  3. 2021On the relationship between disentanglement and multi-task learningcited by 4
  4. 2023Symmetry and Complexity in Object-Centric Deep Active Inference Modelscited by 4
  5. 2022Compositional Law Parsing with Latent Random Functionscited by 3
  6. 2025Unraveling the geometry of visual relational reasoningcited by 3
  7. 2023Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introductioncited by 2
  8. 2024Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selectioncited by 2
  9. 2021DAReN: A Collaborative Approach Towards Reasoning And Disentanglingcited by 1
  10. 2024Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoningcited by 1
  11. 2024Transferring disentangled representations: bridging the gap between synthetic and real imagescited by 1
  12. 2023Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Taskscited by 0
  13. 2023ETHER: Aligning Emergent Communication for Hindsight Experience Replaycited by 0
  14. 2024A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoningcited by 0
  15. 2026XFACTORS: Disentangled Information Bottleneck via Contrastive Supervisioncited by 0
  16. 2026Pretraining Curricula Enable Selective Fine-tuningcited by 0