Towards Robust and Reliable Algorithmic Recourse

Abstract

As predictive models are increasingly being deployed in high-stakes decision making (e.g., loan approvals), there has been growing interest in post hoc techniques which provide recourse to affected individuals. These techniques generate recourses under the assumption that the underlying predictive model does not change. However, in practice, models are often regularly updated for a variety of reasons (e.g., dataset shifts), thereby rendering previously prescribed recourses ineffective. To address this problem, we propose a novel framework, RObust Algorithmic Recourse (ROAR), that leverages adversarial training for finding recourses that are robust to model shifts. To the best of our knowledge, this work proposes the first solution to this critical problem. We also carry out detailed theoretical analysis which underscores the importance of constructing recourses that are robust to model shifts: 1) we derive a lower bound on the probability of invalidation of recourses generated by existing approaches which are not robust to model shifts. 2) we prove that the additional cost incurred due to the robust recourses output by our framework is bounded. Experimental evaluation on multiple synthetic and real-world datasets demonstrates the efficacy of the proposed framework and supports our theoretical findings.

References in corpus (11)

• Actionable Recourse in Linear Classification
• Adversarial Attacks and Defences: A Survey
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
• Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
• Model-Agnostic Counterfactual Explanations for Consequential Decisions
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• On Counterfactual Explanations under Predictive Multiplicity
• Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shifts

Cited by in corpus (16)

• Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions
• Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutions
• Setting the Right Expectations: Algorithmic Recourse Over Time
• A Causal Perspective on Meaningful and Robust Algorithmic Recourse
• On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
• How to Train your Antivirus: RL-based Hardening through the Problem-Space
• RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model
• Endogenous Macrodynamics in Algorithmic Recourse
• A Survey on the Robustness of Feature Importance and Counterfactual Explanations
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
• Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change
• Recourse for reclamation: Chatting with generative language models
• SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies
• Estimation of Counterfactual Interventions under Uncertainties
• Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
• Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions