Robustness Implies Fairness in Causal Algorithmic Recourse

Algorithmic recourse discloses the internal procedures of a black-box decision process where decisions have significant consequences by providing recommendations to empower beneficiaries to achieve a more favorable outcome. To ensure an effective remedy, suggested interventions must not only be cost-effective but also robust and fair. To that end, it is essential to provide similar explanations to similar individuals. This study explores the concept of individual fairness and adversarial robustness in causal algorithmic recourse and addresses the challenge of achieving both. To resolve the challenges, we propose a new framework for defining adversarially robust recourse. That setting observes the protected feature as a pseudometric and demonstrates that individual fairness is a special case of adversarial robustness. Finally, we introduce the fair robust recourse problem and establish solutions to achieve both desirable properties both theoretically and empirically.