ABSTRACT Black‐box explanation methods such as Lime define a neighborhood around the query example, learn an interpretable local surrogate model in this neighborhood, and use this local surrogate model for its explanation. Lore and Anchors are two such methods, which deliver local explanations in the form of IF‐THEN rules. In this article, we argued that such explanations are incomplete because they can miss the specification of the local neighborhood in which they are valid. To counter this, we proposed Glori , an alternative approach which learns globally valid explanations for single examples using the recently proposed Lord rule learner. Our experimental evaluation confirms its improved fidelity, not only for the case when fidelity is measured on an algorithm‐specific neighborhood. Moreover, Glori is considerably more efficient than its neighborhood‐based alternatives.
Huynh et al. (Tue,) studied this question.