Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection (2401.09966v3)

Published 18 Jan 2024 in cs.AI

Abstract: Endowing machines with abstract reasoning ability has been a long-term research topic in artificial intelligence. Raven's Progressive Matrix (RPM) is widely used to probe abstract visual reasoning in machine intelligence, where models will analyze the underlying rules and select one image from candidates to complete the image matrix. Participators of RPM tests can show powerful reasoning ability by inferring and combining attribute-changing rules and imagining the missing images at arbitrary positions of a matrix. However, existing solvers can hardly manifest such an ability in realistic RPM tests. In this paper, we propose a deep latent variable model for answer generation problems through Rule AbstractIon and SElection (RAISE). RAISE can encode image attributes into latent concepts and abstract atomic rules that act on the latent concepts. When generating answers, RAISE selects one atomic rule out of the global knowledge set for each latent concept to constitute the underlying rule of an RPM. In the experiments of bottom-right and arbitrary-position answer generation, RAISE outperforms the compared solvers in most configurations of realistic RPM datasets. In the odd-one-out task and two held-out configurations, RAISE can leverage acquired latent concepts and atomic rules to find the rule-breaking image in a matrix and handle problems with unseen combinations of rules and attributes.

View on arXiv
Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. Measuring abstract reasoning in neural networks. In International conference on machine learning, pp. 511–520. PMLR, 2018.
  2. Scale-localized abstract reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  12557–12565, 2021.
  3. Spatial reasoning. Journal of memory and language, 28(5):564–575, 1989.
  4. Raymond B Cattell. Theory of fluid and crystallized intelligence: A critical experiment. Journal of educational psychology, 54(1):1, 1963.
  5. Roots: Object-centric representation and rendering of 3d scenes. The Journal of Machine Learning Research, 22(1):11770–11805, 2021.
  6. François Chollet. On the measure of intelligence. arXiv preprint arXiv:1911.01547, 2019.
  7. David F Crouse. On implementing 2d rectangular assignment algorithms. IEEE Transactions on Aerospace and Electronic Systems, 52(4):1679–1696, 2016.
  8. Stanislas Dehaene. The number sense: How the mind creates mathematics. OUP USA, 2011.
  9. Towards a neural statistician. In International Conference on Learning Representations, 2017.
  10. Neural scene representation and rendering. Science, 360(6394):1204–1210, 2018.
  11. Meta-learning stationary stochastic process prediction with convolutional neural processes. Advances in Neural Information Processing Systems, 33:8284–8295, 2020.
  12. Time-conditioned generative modeling of object-centric representations for video decomposition and prediction. In Proceedings of the Conference on Uncertainty in Artificial Intelligence, pp.  613–623, 2023.
  13. Neural processes. In ICML 2018 Workshop on Theoretical Foundations and Applications of Deep Generative Models, 2018.
  14. Hierarchical few-shot generative models. In Fifth Workshop on Meta-Learning at the Conference on Neural Information Processing Systems, 2021.
  15. What’s in an object file? evidence from priming studies. Perception & Psychophysics, 58(8):1260–1277, 1996.
  16. Neurobiology of intelligence: science and ethics. Nature Reviews Neuroscience, 5(6):471–482, 2004.
  17. Attention on abstract visual reasoning. arXiv preprint arXiv:1911.05990, 2019.
  18. The variational homoencoder: Learning to learn high capacity generative models from few examples. In Conference on Uncertainty in Artificial Intelligence. Association For Uncertainty in Artificial Intelligence (AUAI), 2018.
  19. Stratified rule-aware network for abstract visual reasoning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  1567–1574, 2021.
  20. Modeling gestalt visual reasoning on raven’s progressive matrices using generative image inpainting techniques. In CogSci, volume 2, pp.  7, 2020.
  21. Solving raven’s progressive matrices with multi-layer relation networks. In 2020 International Joint Conference on Neural Networks (IJCNN), pp.  1–6. IEEE, 2020.
  22. Generative neurosymbolic machines. Advances in Neural Information Processing Systems, 33:12572–12582, 2020.
  23. Simone: View-invariant, temporally-abstracted object representations via unsupervised video decomposition. Advances in Neural Information Processing Systems, 34:20146–20159, 2021.
  24. The reviewing of object files: Object-specific integration of information. Cognitive psychology, 24(2):175–219, 1992.
  25. Attentive neural processes. In International Conference on Learning Representations, 2019.
  26. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  27. One shot learning of simple visual concepts. In Proceedings of the annual meeting of the cognitive science society, volume 33, 2011.
  28. Object-centric learning with slot attention. Advances in Neural Information Processing Systems, 33:11525–11538, 2020.
  29. Deep learning methods for abstract visual reasoning: A survey on raven’s progressive matrices. arXiv preprint arXiv:2201.12382, 2022a.
  30. A review of emerging research directions in abstract visual reasoning. arXiv preprint arXiv:2202.10284, 2022b.
  31. Michael McCloskey. Intuitive physics. Scientific american, 248(4):122–131, 1983.
  32. Melanie Mitchell. Abstraction and analogy-making in artificial intelligence. Annals of the New York Academy of Sciences, 1505(1):79–101, 2021.
  33. Generating correct answers for progressive matrices intelligence tests. arXiv preprint arXiv:2011.00496, 2020.
  34. Raven’s progressive matrices and vocabulary scales, volume 759. Oxford pyschologists Press Oxford, 1998.
  35. Raven’s progressive matrices completion with latent gaussian process priors. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  9612–9620, 2021.
  36. Compositional law parsing with latent random functions. In International Conference on Learning Representations, 2023.
  37. Learning structured output representation using deep conditional generative models. Advances in neural information processing systems, 28, 2015.
  38. Ladder variational autoencoders. Advances in neural information processing systems, 29:3738–3746, 2016.
  39. Improving generalization for abstract reasoning tasks using disentangled feature representations. arXiv preprint arXiv:1811.04784, 2018.
  40. Attention is all you need. Advances in neural information processing systems, 30, 2017.
  41. Abstract diagrammatic reasoning with multiplex graph networks. In International Conference on Learning Representations, 2019.
  42. Abstract diagrammatic reasoning with multiplex graph networks. arXiv preprint arXiv:2006.11197, 2020.
  43. Gaussian processes for machine learning, volume 2. MIT press Cambridge, MA, 2006.
  44. The scattering compositional learner: Discovering objects, attributes, relationships in analogical reasoning. arXiv preprint arXiv:2007.04212, 2020.
  45. Unsupervised learning of compositional scene representations from multiple unspecified viewpoints. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pp.  8971–8979, 2022.
  46. Compositional scene representation learning via reconstruction: A survey. IEEE Transactions on Pattern Analysis & Machine Intelligence, 45(10):11540–11560, 2023.
  47. Unsupervised object-centric learning from multiple unspecified viewpoints. IEEE Transactions on Pattern Analysis & Machine Intelligence, in press.
  48. Raven: A dataset for relational and analogical visual reasoning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  5317–5327, 2019a.
  49. Learning perceptual inference by contrasting. arXiv preprint arXiv:1912.00086, 2019b.
  50. Abstract spatial-temporal reasoning via probabilistic abduction and execution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.  9736–9746, 2021a.
  51. Learning algebraic representation for systematic generalization in abstract reasoning. arXiv preprint arXiv:2111.12990, 2021b.
  52. Abstract reasoning with distracting features. Advances in Neural Information Processing Systems, 32, 2019.
  53. Effective abstract reasoning with dual-contrast network. In International Conference on Learning Representations, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Fan Shi (26 papers)
  2. Bin Li (514 papers)
  3. Xiangyang Xue (169 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets