On the Power and Limitations of Examples for Description Logic Concepts

On the Power and Limitations of Examples for Description Logic Concepts

Balder ten Cate, Raoul Koudijs, Ana Ozaki

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence
Main Track. Pages 3567-3575. https://doi.org/10.24963/ijcai.2024/395

Labeled examples (i.e., positive and negative examples) are an attractive medium for communicating complex concepts. They are useful for deriving concept expressions (such as in concept learning, interactive concept specification, and concept refinement) as well as for illustrating concept expressions to a user or domain expert. We investigate the power of labeled examples for describing description-logic concepts. Specifically, we systematically study the existence and efficient computability of finite characterizations, i.e. finite sets of labeled examples that uniquely characterize a single concept, for a wide variety of description logics between EL and ALCQI, both without an ontology and in the presence of a DL-Lite ontology. Finite characterizations are relevant for debugging purposes, and their existence is a necessary condition for exact learnability with membership queries.
Keywords:
Knowledge Representation and Reasoning: KRR: Learning and reasoning
Knowledge Representation and Reasoning: KRR: Description logics and ontologies
Machine Learning: ML: Learning theory