Timezone: »
The Abstraction and Reasoning Corpus (ARC) aims at benchmarking the performance of general artificial intelligence algorithms. The ARC's focus on broad generalization and few-shot learning has made it impossible to solve using pure machine learning. A more promising approach has been to perform program synthesis within an appropriately designed Domain Specific Language (DSL). However, these too have seen limited success. We propose Abstract Reasoning with Graph Abstractions (ARGA), a new object-centric framework that first represents images using graphs and then performs a constraint-guided search for a correct program in a DSL that is based on the abstracted graph space. Early experiments demonstrates the promise of ARGA in tackling some of the complicated tasks of the ARC rather efficiently, producing programs that are correct and easy to understand.
Author Information
Yudong Xu (University of Toronto)
Elias Khalil (University of Toronto)
Scott Sanner (University of Toronto)
More from the Same Authors
-
2022 : PyEPO: A PyTorch-based End-to-End Predict-then-Optimize Library with Linear Objective Function »
Bo Tang · Elias Khalil -
2022 Poster: Learning to Follow Instructions in Text-Based Games »
Mathieu Tuli · Andrew Li · Pashootan Vaezipoor · Toryn Klassen · Scott Sanner · Sheila McIlraith -
2022 Poster: Neur2SP: Neural Two-Stage Stochastic Programming »
Rahul Mihir Patel · Justin Dumouchelle · Elias Khalil · Merve Bodur -
2022 Poster: A Deep Reinforcement Learning Framework for Column Generation »
Cheng Chi · Amine Aboussalah · Elias Khalil · Juyoung Wang · Zoha Sherkat-Masoumi -
2021 : Machine Learning for Combinatorial Optimization + Q&A »
Maxime Gasse · Simon Bowly · Chris Cameron · Quentin Cappart · Jonas Charfreitag · Laurent Charlin · Shipra Agrawal · Didier Chetelat · Justin Dumouchelle · Ambros Gleixner · Aleksandr Kazachkov · Elias Khalil · Pawel Lichocki · Andrea Lodi · Miles Lubin · Christopher Morris · Dimitri Papageorgiou · Augustin Parjadis · Sebastian Pokutta · Antoine Prouvost · Yuandong Tian · Lara Scavuzzo · Giulia Zarpellon -
2021 Poster: Risk-Aware Transfer in Reinforcement Learning using Successor Features »
Michael Gimelfarb · Andre Barreto · Scott Sanner · Chi-Guhn Lee -
2021 Poster: Learning to Schedule Heuristics in Branch and Bound »
Antonia Chmiela · Elias Khalil · Ambros Gleixner · Andrea Lodi · Sebastian Pokutta -
2021 Poster: Representer Point Selection via Local Jacobian Expansion for Post-hoc Classifier Explanation of Deep Neural Networks and Ensemble Models »
Yi Sui · Ga Wu · Scott Sanner -
2020 Poster: Hybrid Models for Learning to Branch »
Prateek Gupta · Maxime Gasse · Elias Khalil · Pawan K Mudigonda · Andrea Lodi · Yoshua Bengio -
2012 Poster: Symbolic Dynamic Programming for Continuous State and Observation POMDPs »
Zahra Zamani · Scott Sanner · Pascal Poupart · Kristian Kersting -
2011 Workshop: Choice Models and Preference Learning »
Jean-Marc Andreoli · Cedric Archambeau · Guillaume Bouchard · Shengbo Guo · Kristian Kersting · Scott Sanner · Martin Szummer · Paolo Viappiani · Onno Zoeter -
2010 Poster: Gaussian Process Preference Elicitation »
Edwin Bonilla · Shengbo Guo · Scott Sanner