Robustness Implies Fairness in Causal Algorithmic Recourse

Algorithmic Recourse refers to the capability of an algorithm to provide explanations and make recommendations in response to an appeal or challenge raised by an individual who has been affected negatively by its decision Wachter et al. (2017); Ustun et al. (2019); Karimi et al. (2020); Venkatasubramanian and Alfano (2020). This concept is particularly important in areas such as finance, healthcare, and criminal justice where decisions made by algorithms can have significant impacts on people's lives Chou et al. (2022). Recently, there has been an explosion of proposals for counterfactual explainers in the emerging field of algorithmic recourse Guidotti (2022); Stepin et al. (2021); Karimi et al. (2021); Verma et al. (2020). Ensuring fairness and robustness in algorithmic decision-making processes is crucial to guarantee fair and just outcomes for all involved. In the context of algorithmic recourse, robustness refers to the ability of an algorithm to withstand unreliability, manipulation, or deception by malicious actors, while still providing fair and accurate recourse recommendations Slack et al. (2021); Upadhyay et al. (2021); Dominguez-Olmedo et al. (2022); Pawelczyk et al. (2022). There are four types of unreliabilities in counterfactual explanations Mishra et al. (2021): Robustness to input perturbations: Examining recourse behavior in response to slight input changes while the classifier remains unchanged Dominguez-Olmedo et al. (2022).