Interpretable Counterfactual Explanations Guided by Prototypes

• Published in: Machine Learning and Knowledge Discovery in Databases. Research Track Vol. 12976; pp. 650 - 665
• Main Authors: Van Looveren, Arnaud, Klaise, Janis
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Counterfactual explanations; Interpretation; Transparency/Explainability
• ISBN: 3030865193; 9783030865191
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-86520-7_40

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific k-d trees, significantly speed up the search for counterfactua...