Improvement-Focused Causal Recourse (ICR)
DOI:
https://doi.org/10.1609/aaai.v37i10.26398Keywords:
PEAI: Interpretability and Explainability, ML: Causal Learning, PEAI: Philosophical Foundations of AI, RU: Causality, RU: Graphical ModelAbstract
Algorithmic recourse recommendations inform stakeholders of how to act to revert unfavorable decisions. However, existing methods may recommend actions that lead to acceptance (i.e., revert the model's decision) but do not lead to improvement (i.e., may not revert the underlying real-world state). To recommend such actions is to recommend fooling the predictor. We introduce a novel method, Improvement-Focused Causal Recourse (ICR), which involves a conceptual shift: Firstly, we require ICR recommendations to guide toward improvement. Secondly, we do not tailor the recommendations to be accepted by a specific predictor. Instead, we leverage causal knowledge to design decision systems that predict accurately pre- and post-recourse, such that improvement guarantees translate into acceptance guarantees. Curiously, optimal pre-recourse classifiers are robust to ICR actions and thus suitable post-recourse. In semi-synthetic experiments, we demonstrate that given correct causal knowledge ICR, in contrast to existing approaches, guides toward both acceptance and improvement.Downloads
Published
2023-06-26
How to Cite
König, G., Freiesleben, T., & Grosse-Wentrup, M. (2023). Improvement-Focused Causal Recourse (ICR). Proceedings of the AAAI Conference on Artificial Intelligence, 37(10), 11847-11855. https://doi.org/10.1609/aaai.v37i10.26398
Issue
Section
AAAI Technical Track on Philosophy and Ethics of AI