Abductive Explanations of Classifiers under Constraints: Complexity and Properties

Martin Cooper (1, 2, 3, 4) , Leila Amgoud (1, 5, 4)

1 IRIT-ADRIA - Argumentation, Décision, Raisonnement, Incertitude et Apprentissage
2 UT3 - Université Toulouse III - Paul Sabatier
3 UT - Université de Toulouse
4 IRIT - Institut de recherche en informatique de Toulouse
5 CNRS - Centre National de la Recherche Scientifique

Abductive explanations (AXp's) are widely used for understanding decisions of classifiers. Existing definitions are suitable when features are independent. However, we show that ignoring constraints when they exist between features may lead to an explosion in the number of redundant or superfluous AXp's. We propose three new types of explanations that take into account constraints and that can be generated from the whole feature space or from a sample (such as a dataset). They are based on a key notion of coverage of an explanation, the set of instances it explains. We show that coverage is powerful enough to discard redundant and superfluous AXp's. For each type, we analyse the complexity of finding an explanation and investigate its formal properties. The final result is a catalogue of different forms of AXp's with different complexities and different formal guarantees.

Domaines: Informatique [cs]

Martin Cooper, Leila Amgoud. Abductive Explanations of Classifiers under Constraints: Complexity and Properties. 26th European Conference on Artificial Intelligence (ECAI 2023), European Association for Artificial Intelligence (EurAI); Polish Artificial Intelligence Society (PSSI), Sep 2023, Krakow, Poland. à paraître, ⟨10.3233/FAIA230305⟩. ⟨hal-04210428v1⟩