Learning Logic Programs by Discovering Higher-Order Abstractions

08/16/2023
by   Céline Hocquette, et al.
0

Discovering novel abstractions is important for human-level AI. We introduce an approach to discover higher-order abstractions, such as map, filter, and fold. We focus on inductive logic programming, which induces logic programs from examples and background knowledge. We introduce the higher-order refactoring problem, where the goal is to compress a logic program by introducing higher-order abstractions. We implement our approach in STEVIE, which formulates the higher-order refactoring problem as a constraint optimisation problem. Our experimental results on multiple domains, including program synthesis and visual reasoning, show that, compared to no refactoring, STEVIE can improve predictive accuracies by 27 47 different domains

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset