Skip to main content
Springer Nature Link
Log in

Tackling the Abstraction and Reasoning Corpus (ARC) with Object-Centric Models and the MDL Principle

  • Conference paper
  • First Online:
Advances in Intelligent Data Analysis XXII (IDA 2024)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 14641))

Included in the following conference series:

  • 653 Accesses

Abstract

The Abstraction and Reasoning Corpus (ARC) is a challenging benchmark, introduced to foster AI research towards human-like intelligence. It is a collection of unique tasks about generating colored grids, specified by a few examples only. In contrast to the transformation-based programs of existing work, we introduce object-centric models that are in line with the natural programs produced by humans. Our models can not only perform predictions, but also provide joint descriptions for input/output pairs. The Minimum Description Length (MDL) principle is used to efficiently search the large model space. A diverse range of tasks are solved, and the learned models are similar to natural programs.

S. Ferré: This research is supported by Labex Cominlabs (ANR-10-LABX-07-01).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Data and testing interface at https://github.com/fchollet/ARC.

  2. 2.

    https://www.kaggle.com/c/abstraction-and-reasoning-challenge.

  3. 3.

    https://lab42.global/past-challenges/arcathon-2022/.

  4. 4.

    Open source available at https://github.com/sebferre/ARC-MDL.

References

  1. Acquaviva, S., et al.: Communicating natural programs to humans and machines. Adv. Neural. Inf. Process. Syst. 35, 3731–3743 (2022)

    Google Scholar 

  2. Ainooson, J., Sanyal, D., Michelson, J.P., Yang, Y., Kunda, M.: An approach for solving tasks on the abstract reasoning corpus. arXiv preprint arXiv:2302.09425 (2023)

  3. Alford, S., et al.: Neural-guided, bidirectional program search for abstraction and reasoning. CoRR abs/2110.11536 (2021)

    Google Scholar 

  4. Chollet, F.: A definition of intelligence for the real world. J. Artif. Gen. Intell. 11(2), 27–30 (2020)

    Google Scholar 

  5. Ellis, K., et al.: DreamCoder: bootstrapping inductive program synthesis with wake-sleep library learning. In: PLDI 2021: Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, pp. 835–850 (2021)

    Google Scholar 

  6. Ferré, S.: Tackling the abstraction and reasoning corpus (ARC) with object-centric models and the MDL principle. arXiv preprint arXiv:2311.00545 (2023)

  7. Fischer, R., Jakobs, M., Mücke, S., Morik, K.: Solving abstract reasoning tasks with grammatical evolution. In: LWDA, pp. 6–10. CEUR-WS 2738 (2020)

    Google Scholar 

  8. Goertzel, B.: Artificial general intelligence: concept, state of the art, and future prospects. J. Artif. Gen. Intell. 5(1), 1 (2014)

    Article  Google Scholar 

  9. Grünwald, P., Roos, T.: Minimum description length revisited. Int. J. Math. Ind. 11(01), 1930001 (2019)

    Article  MathSciNet  Google Scholar 

  10. Johnson, A., Vong, W.K., Lake, B., Gureckis, T.: Fast and flexible: human program induction in abstract reasoning tasks. arXiv preprint arXiv:2103.05823 (2021)

  11. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 25, 1097–1105 (2012)

    Google Scholar 

  12. Lieberman, H.: Your Wish is My Command. The Morgan Kaufmann series in interactive technologies, Morgan Kaufmann / Elsevier (2001)

    Google Scholar 

  13. Menon, A., Tamuz, O., Gulwani, S., Lampson, B., Kalai, A.: A machine learning framework for programming by example. In: International Conference on Machine Learning, pp. 187–195. PMLR (2013)

    Google Scholar 

  14. Rissanen, J.: Modeling by shortest data description. Automatica 14(5), 465–471 (1978)

    Article  Google Scholar 

  15. Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484–489 (2016)

    Article  Google Scholar 

  16. Vreeken, J., Van Leeuwen, M., Siebes, A.: Krimp: mining itemsets that compress. Data Min. Knowl. Disc. 23(1), 169–214 (2011). https://doi.org/10.1007/s10618-010-0202-x

    Article  MathSciNet  Google Scholar 

  17. Xu, Y., Khalil, E.B., Sanner, S.: Graphs, constraints, and search for the abstraction and reasoning corpus. arXiv preprint arXiv:2210.09880 (2022)

Download references

Author information

Authors and Affiliations

  1. Univ Rennes, CNRS, Inria, IRISA, Campus de Beaulieu, 35042, Rennes, France

    Sébastien Ferré

Authors
  1. Sébastien Ferré
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sébastien Ferré .

Editor information

Editors and Affiliations

  1. Stockholm University, Kista, Sweden

    Ioanna Miliou

  2. Fraunhofer IAIS, Sankt Augustin, Germany

    Nico Piatkowski

  3. Stockholm University, Kista, Sweden

    Panagiotis Papapetrou

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Ferré, S. (2024). Tackling the Abstraction and Reasoning Corpus (ARC) with Object-Centric Models and the MDL Principle. In: Miliou, I., Piatkowski, N., Papapetrou, P. (eds) Advances in Intelligent Data Analysis XXII. IDA 2024. Lecture Notes in Computer Science, vol 14641. Springer, Cham. https://doi.org/10.1007/978-3-031-58547-0_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-58547-0_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-58546-3

  • Online ISBN: 978-3-031-58547-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics