mlsanityData to 7 Oct 2026

The Scattering Compositional Learner: Discovering Objects, Attributes, Relationships in Analogical Reasoning

arXiv 2007.04212 ↗First posted 8 Jul 2020cs.LG cs.AI cs.LOcited by 46

Not on the map. Why?

Cited by 31 in LLM reasoning, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In this work, we focus on an analogical reasoning task that contains rich compositional structures, Raven's Progressive Matrices (RPM). To discover compositional structures of the data, we propose the Scattering Compositional Learner (SCL), an architecture that composes neural networks in a sequence. Our SCL achieves state-of-the-art performance on two RPM datasets, with a 48.7% relative improvement on Balanced-RAVEN and 26.4% on PGM over the previous state-of-the-art. We additionally show that our model discovers compositional representations of objects' attributes (e.g., shape color, size), and their relationships (e.g., progression, union). We also find that the compositional representation makes the SCL significantly more robust to test-time domain shifts and greatly improves zero-shot generalization to previously unseen analogies.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). First posted on arXiv 8 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 11; 2023: 9; 2024: 13; 2025: 7; 2026: 2.

46 papers.

Sort:

By area:

  1. 2022Emergent Analogical Reasoning in Large Language Modelscited by 239
  2. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  3. 2022A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matricescited by 64
  4. 2022A Benchmark for Compositional Visual Reasoningcited by 43
  5. 2022Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matricescited by 37
  6. 2022A Review of Emerging Research Directions in Abstract Visual Reasoningcited by 33
  7. 2021Learning Algebraic Representation for Systematic Generalization in Abstract Reasoningcited by 27
  8. 2021Dynamic Inference with Neural Interpreterscited by 24
  9. 2023Learning to reason over visual objectscited by 19
  10. 2022Evaluating Understanding on Conceptual Abstraction Benchmarkscited by 13
  11. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
  12. 2022SAViR-T: Spatially Attentive Visual Reasoning with Transformerscited by 9
34 more
  1. 2024Probabilistic Abduction for Visual Abstract Reasoning via Learning Rules in Vector-symbolic Architecturescited by 9
  2. 2024REFACTOR: Learning to Extract Theorems from Proofscited by 9
  3. 2024Towards Learning Abductive Reasoning using VSA Distributed Representationscited by 9
  4. 2022Interactive Visual Reasoning under Uncertaintycited by 8
  5. 2021Abstract Reasoning via Logic-guided Generationcited by 7
  6. 2022Multi-Viewpoint and Multi-Evaluation with Felicitous Inductive Bias Boost Machine Abstract Reasoning Abilitycited by 7
  7. 2024Towards Learning to Reason: Comparing LLMs with Neuro-Symbolic on Arithmetic Relations in Abstract Reasoningcited by 7
  8. 2023Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problemscited by 6
  9. 2023One Self-Configurable Model to Solve Many Abstract Visual Reasoning Problemscited by 6
  10. 2025Can Large Reasoning Models do Analogical Reasoning under Perceptual Uncertainty?cited by 5
  11. 2022Knowledge-based Analogical Reasoning in Neuro-symbolic Latent Spacescited by 4
  12. 2023A Cognitively-Inspired Neural Architecture for Visual Abstract Reasoning Using Contrastive Perceptual and Conceptual Processingcited by 4
  13. 2024A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoningcited by 4
  14. 2024Learning Visual Abstract Reasoning through Dual-Stream Networkscited by 4
  15. 2022Compositional Law Parsing with Latent Random Functionscited by 3
  16. 2025Unraveling the geometry of visual relational reasoningcited by 3
  17. 2023Computational Models of Solving Raven's Progressive Matrices: A Comprehensive Introductioncited by 2
  18. 2024Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selectioncited by 2
  19. 2024Triple-CFN: Separating Concepts and Features Enhances Machine Abstract Reasoning Abilitycited by 2
  20. 2023Does Visual Pretraining Help End-to-End Reasoning?cited by 1
  21. 2023Learning Abstract Visual Reasoning via Task Decomposition: A Case Study in Raven Progressive Matricescited by 1
  22. 2024A Unified View of Abstract Visual Reasoning Problemscited by 1
  23. 2024Funny-Valen-Tine: Planning Solution Distribution Enhances Machine Abstract Reasoning Abilitycited by 1
  24. 2025Systematic Abductive Reasoning via Diverse Relation Representations in Vector-symbolic Architecturecited by 1
  25. 2023Deep Non-Monotonic Reasoning for Visual Abstract Reasoning Taskscited by 0
  26. 2023Emergent Communication for Rules Reasoningcited by 0
  27. 2024D4C: Improving Negative Example Quality to Enhance Machine Abstract Reasoning Abilitycited by 0
  28. 2024A Feature-based Generalizable Prediction Model for Both Perceptual and Abstract Reasoningcited by 0
  29. 2025GenVP: Generating Visual Puzzles with Contrastive Hierarchical VAEscited by 0
  30. 2025Advancing Generalization Across a Variety of Abstract Visual Reasoning Taskscited by 0
  31. 2025Johnny: Structuring Representation Space to Enhance Machine Abstract Reasoning Abilitycited by 0
  32. 2025Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoningcited by 0
  33. 2026Predictive Reasoning with Augmented Anomaly Contrastive Learning for Compositional Visual Relationscited by 0
  34. 2026DIRCR: Dual-Inference Rule-Contrastive Reasoning for Solving RAVENscited by 0