Generalisation Through Negation and Predicate Invention
This addresses the problem of few-shot learning for AI systems, though it appears incremental as it builds on existing ILP methods.
The paper tackles the challenge of generalizing from few examples by introducing an inductive logic programming approach that combines negation and predicate invention, resulting in improved predictive accuracies and learning times across multiple domains.
The ability to generalise from a small number of examples is a fundamental challenge in machine learning. To tackle this challenge, we introduce an inductive logic programming (ILP) approach that combines negation and predicate invention. Combining these two features allows an ILP system to generalise better by learning rules with universally quantified body-only variables. We implement our idea in NOPI, which can learn normal logic programs with predicate invention, including Datalog programs with stratified negation. Our experimental results on multiple domains show that our approach can improve predictive accuracies and learning times.