A Causal Perspective on Meaningful and Robust Algorithmic Recourse

A Causal Perspective on Meaningful and Robust Algorithmic Recourse

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.

Grafik Top
Authors
  • König, Gunnar
  • Freiesleben, Timo
  • Grosse-Wentrup, Moritz
Grafik Top
Shortfacts
Category
Paper in Conference Proceedings or in Workshop Proceedings (Paper)
Event Title
ICML Workshop on Algorithmic Recourse
Divisions
Neuroinformatics
Event Location
Virtual
Event Type
Workshop
Event Dates
July 24, 2021
Date
24 July 2021
Export
Grafik Top