mlsanityData to 7 Oct 2026

Abstract Reasoning with Distracting Features

arXiv 1912.00569 ↗First posted 2 Dec 2019cs.AI cs.CLcited by 33

Not on the map. Why?

Abstract (arXiv)

Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we first illustrate that one of the main challenges in such a reasoning task is the presence of distracting features, which requires the learning algorithm to leverage counterevidence and to reject any of the false hypotheses in order to learn the true patterns. We later show that carefully designed learning trajectory over different categories of training data can effectively boost learning performance by mitigating the impacts of distracting features. Inspired by this fact, we propose feature robust abstract reasoning (FRAR) model, which consists of a reinforcement learning based teacher network to determine the sequence of training and a student network for predictions. Experimental results demonstrated strong improvements over baseline algorithms and we are able to beat the state-of-the-art models by 18.7% in the RAVEN dataset and 13.3% in the PGM dataset.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 7; 2023: 6; 2024: 7; 2025: 2; 2026: 1.

33 papers.

Sort:

By area:

  1. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  2. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  3. 2021Abstract Spatial-Temporal Reasoning via Probabilistic Abduction and Executioncited by 43
  4. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  5. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  6. 2021ACRE: Abstract Causal REasoning Beyond Covariationcited by 30
  7. 2021Learning Algebraic Representation for Systematic Generalization in Abstract Reasoningcited by 27
  8. 2022Effective Abstract Reasoning with Dual-Contrast Networkcited by 23
  9. 2023Learning to reason over visual objectscited by 19
  10. 2021Selective Replay Enhances Learning in Online Continual Analogical Reasoningcited by 12
  11. 2021Unsupervised Abstract Reasoning for Raven's Problem Matricescited by 12
  12. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
21 more
  1. 2022SAViR-T: Spatially Attentive Visual Reasoning with Transformerscited by 9
  2. 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matricescited by 9
  3. 2022Interactive Visual Reasoning under Uncertaintycited by 8
  4. 2021Abstract Reasoning via Logic-guided Generationcited by 7
  5. 2021Two-stage Rule-induction Visual Reasoning on RPMs with an Application to Video Predictioncited by 7
  6. 2022Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Abilitycited by 7
  7. 2023Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problemscited by 6
  8. 2023One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problemscited by 6
  9. 2023A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processingcited by 4
  10. 2024Sandra -- A Neuro-Symbolic Reasoner Based On Descriptions And Situationscited by 4
  11. 2024Learning Visual Abstract Reasoning through Dual-Stream Networkscited by 4
  12. 2021Data augmentation by morphological mixup for solving Raven's Progressive Matricescited by 2
  13. 2024Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selectioncited by 2
  14. 2024Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Abilitycited by 2
  15. 2024Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Abilitycited by 1
  16. 2025Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecturecited by 1
  17. 2021A One-Shot Texture-Perceiving Generative Adversarial Network for Unsupervised Surface Inspectioncited by 0
  18. 2023Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Taskscited by 0
  19. 2024D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Abilitycited by 0
  20. 2025DIO: Refining Mutual Information and Causal Chain to Enhance Machine Abstract Reasoning Abilitycited by 0
  21. 2026DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENscited by 0