Knowledge refactoring for inductive program synthesis

Conference item

Humans constantly restructure knowledge to use it more efficiently. Our goal is to give a machine learning system similar abilities so that it can learn more efficiently. We introduce the knowledge refactoring problem, where the goal is to restructure a learner's knowledge base to reduce its size and to minimise redundancy in it. We focus on inductive logic programming, where the knowledge base is a logic program. We introduce Knorf, a system which solves the refactoring problem using constraint optimisation. A key feature of Knorf is that, rather than simply removing knowledge, it also introduces new knowledge through predicate invention. We evaluate our approach on two domains: building Lego structures and real-world string transformations. Our experiments show that learning from refactored knowledge can improve predictive accuracies fourfold and reduce learning times by half.

Authors: Dumancic, S; Guns, T; Cropper, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Association for the Advancement of Artificial Intelligence
• Host title: Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI-21)
• Volume: 35
• Issue: 8
• Pages: 7271-7278
• Publication date: 2021-05-18
• Event title: 35th AAAI Conference on Artificial Intelligence (AAAI-21)
• Event website: https://aaai.org/Conferences/AAAI-21/
• Event start date: 2021-02-02
• Event end date: 2021-02-09
• EISSN: 2374-3468
• ISSN: 2159-5399
• ISBN: 978-1-57735-866-4
• Language: English
• Keywords: FFR