Mixed-World Reasoning with Existential Rules under Active-Domain Semantics

Meghyn Bienvenu (1, 2, 3) , Pierre Bourhis (4, 5, 2, 6)

1 LaBRI - Laboratoire Bordelais de Recherche en Informatique
2 CNRS - Centre National de la Recherche Scientifique
3 UB - Université de Bordeaux
4 Inria Lille - Nord Europe
5 Université de Lille
6 SPIRALS - Self-adaptation for distributed services and large software systems

In this paper, we study reasoning with existential rules in a setting where some of the predicates may be closed (i.e., their content is fully specified by the data instance) and the remaining open predicates are interpreted under active-domain semantics. We show, unsurprisingly, that the main reasoning tasks (satisfiability and certainty / possibility of Boolean queries) are all intractable in data complexity in the general case. However, several positive (PTIME data) results are obtained for the linear fragment, and interestingly, these tractability results hold also for various extensions, e.g., with negated closed atoms and disjunctive rule heads. This motivates us to take a closer look at the linear fragment, exploring its expressivity and defining a fixpoint extension to approximate non-linear rules.

Domaines: Intelligence artificielle [cs.AI]

Meghyn Bienvenu, Pierre Bourhis. Mixed-World Reasoning with Existential Rules under Active-Domain Semantics. Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), Aug 2019, Macao, Macau SAR China. ⟨10.24963/ijcai.2019/216⟩. ⟨hal-02342129⟩