A Causal Perspective on Meaningful and Robust Algorithmic Recourse

MCML Authors

Gunnar König

Dr.

* Former Member

→ Group Bernd Bischl
 Statistical Learning and Data Science

Moritz Grosse-Wentrup

Prof. Dr.

Principal Investigator

* Former Principal Investigator

Abstract

Algorithmic recourse explanations inform stakeholders on how to act to revert unfavorable predictions. However, in general ML models do not predict well in interventional distributions. Thus, an action that changes the prediction in the desired way may not lead to an improvement of the underlying target. Such recourse is neither meaningful nor robust to model refits. Extending the work of Karimi et al. (2021), we propose meaningful algorithmic recourse (MAR) that only recommends actions that improve both prediction and target. We justify this selection constraint by highlighting the differences between model audit and meaningful, actionable recourse explanations. Additionally, we introduce a relaxation of MAR called effective algorithmic recourse (EAR), which, under certain assumptions, yields meaningful recourse by only allowing interventions on causes of the target.

inproceedings KFG21

---

Algorithmic Recourse @ICML 2021

Workshop on Algorithmic Recourse at the 38th International Conference on Machine Learning. Virtual, Jul 18-24, 2021.

---

Authors

G. König • T. Freiesleben • M. Grosse-Wentrup

---

Links

URL

---

Research Area

 A1 | Statistical Foundations & Explainability