Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems

Abstract

Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set of changes a person can undertake in order to improve their outcome. We propose a recourse algorithm that models the underlying data distribution or manifold. We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome. This mechanism can be easily used to provide recourse for any differentiable machine learning based decision making system. Further, the resulting algorithm is shown to be applicable to both supervised classification and causal decision making systems. Our work attempts to fill gaps in existing fairness literature that have primarily focused on discovering and/or algorithmically enforcing fairness constraints on decision making systems. This work also provides an alternative approach to generating counterfactual explanations.

References in corpus (7)

• Auto-Encoding Variational Bayes
• Tutorial on Variational Autoencoders
• Adversarial Feature Learning
• Adversarially Learned Inference
• Actionable Recourse in Linear Classification
• Causal Effect Inference with Deep Latent-Variable Models
• Interpretable Credit Application Predictions With Counterfactual Explanations

Cited by in corpus (42)

• Deep Neural Networks and Tabular Data: A Survey
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methods
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• Algorithmic Recourse: from Counterfactual Explanations to Interventions
• The Conflict Between Explainable and Accountable Decision-Making Algorithms
• A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
• A Survey on Causal Inference for Recommendation
• What-is and How-to for Fairness in Machine Learning: A Survey, Reflection, and Perspective
• Generating collective counterfactual explanations in score-based classification via mathematical optimization
• Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
• Model extraction from counterfactual explanations
• On Counterfactual Explanations under Predictive Multiplicity
• GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
• Consequence-aware Sequential Counterfactual Generation
• From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
• Evaluations and Methods for Explanation through Robustness Analysis
• Latent-CF: A Simple Baseline for Reverse Counterfactual Explanations
• Counterfactual Learning on Graphs: A Survey
• Explanation by Progressive Exaggeration
• CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms
• Algorithmic Recourse in the Wild: Understanding the Impact of Data and Model Shifts
• Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertainties
• Consistent Counterfactuals for Deep Models
• Conditional Generative Models for Counterfactual Explanations
• Endogenous Macrodynamics in Algorithmic Recourse
• Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis
• Failure Modes of Variational Autoencoders and Their Effects on Downstream Tasks
• DISSECT: Disentangled Simultaneous Explanations via Concept Traversals
• Framing Algorithmic Recourse for Anomaly Detection
• Extracting Incentives from Black-Box Decisions
• Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
• Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning
• DeDUCE: Generating Counterfactual Explanations Efficiently
• Explaining the Behavior of Black-Box Prediction Algorithms with Causal Learning
• Strategic Classification Made Practical
• MCCE: Monte Carlo sampling of realistic counterfactual explanations
• SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies
• A Decentralized Approach towards Responsible AI in Social Ecosystems
• Explainability Requires Interactivity
• Counterfactual Explanations via Latent Space Projection and Interpolation
• Low-Cost Algorithmic Recourse for Users With Uncertain Cost Functions