Multi-Objective Counterfactual Explanations

MCML Authors

Susanne Dandl

Dr.

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Martin Binder

→ Group Bernd Bischl
 Statistical Learning and Data Science

Bernd Bischl

Prof. Dr.

Director

Statistical Learning and Data Science

Abstract

Counterfactual explanations are one of the most popular methods to make predictions of black box machine learning models interpretable by providing explanations in the form of ‘what-if scenarios’. Most current approaches optimize a collapsed, weighted sum of multiple objectives, which are naturally difficult to balance a-priori. We propose the Multi-Objective Counterfactuals (MOC) method, which translates the counterfactual search into a multi-objective optimization problem. Our approach not only returns a diverse set of counterfactuals with different trade-offs between the proposed objectives, but also maintains diversity in feature space. This enables a more detailed post-hoc analysis to facilitate better understanding and also more options for actionable user responses to change the predicted outcome. Our approach is also model-agnostic and works for numerical and categorical input features. We show the usefulness of MOC in concrete cases and compare our approach with state-of-the-art methods for counterfactual explanations.

inproceedings DMB+20

---

PPSN 2020

16th International Conference on Parallel Problem Solving from Nature. Leiden, Netherlands, Sep 05-09, 2020.

---

Authors

S. Dandl • C. Molnar • M. Binder • B. Bischl

---

Links

DOI

---

Research Area

 A1 | Statistical Foundations & Explainability