Algorithmic recourse addresses the challenge of providing tailored recommendations to users affected by unfavorable machine learning decisions, particularly in high-stakes scenarios.
Traditional approaches to recourse often rely on the closest counterfactual explanations or assume a priori knowledge of a user's causal structure, resulting in interventions that overlook individual contexts and specific feature interactions.
To overcome these limitations, we study a human-in-the-loop framework that iteratively approximates the user's structural causal model through interactive queries via Bayesian inference before producing recourse recommendations.
This framework exploits human feedback to improve the identification of causal effects, allowing personalized recourse that is plausible, cost-effective, and aligned with the actual causal dependencies of each user.
As a proof of concept, we evaluate this framework through simulated human responses. Our simulations across linear and non-linear causal models show promising results, though challenges remain in capturing complex, non-linear structures, emphasizing the importance of accurate approximations and robust noise distribution modeling.
Blogger's Review: This paper presents an innovative human-in-the-loop framework for personalized causal recourse, enhancing causal model identification through user feedback. Its potential applications are vast, yet further research is required to effectively capture complex non-linear structures to ensure the model's reliability and efficacy.