A model-agnostic, network theory-based framework for supporting XAI on classifiers

Gianluca Bonifazi, Francesco Cauteruccio, Enrico Corradini, Michele Marchetti, Giorgio Terracina, Domenico Ursino, Luca Virgili

Abstract: Highlights•Performing model-agnostic Explainable AI on classifiers.•Introducing the concept of dyscrasia of feature occurrences.•Assessing the relevance of a feature during classification.