{Bram Steenwinckel Gilles Vandewiele Femke Ongenae Filip De Turck}

Abstract

Deep-learning based techniques are increasingly being used for different machine learning tasks on knowledge graphs. While it has been shown empirically that these techniques often achieve better predictive performances than their classical counterparts, where features are extracted from the graph, they lack interpretability. Interpretability is a vital aspect in critical domains such as the health and financial sector. In this paper, we present a technique that builds a decision tree of class-specific substructures in order to classify different entities within the knowledge graph. We show how our proposed technique is competitive to current state-of-the-art deep-learning techniques on four benchmark datasets, while being fully interpretable.