Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses

Abstract

As predictive models are increasingly being deployed in high-stakes decision-making, there has been a lot of interest in developing algorithms which can provide recourses to affected individuals. While developing such tools is important, it is even more critical to analyse and interpret a predictive model, and vet it thoroughly to ensure that the recourses it offers are meaningful and non-discriminatory before it is deployed in the real world. To this end, we propose a novel model agnostic framework called Actionable Recourse Summaries (AReS) to construct global counterfactual explanations which provide an interpretable and accurate summary of recourses for the entire population. We formulate a novel objective which simultaneously optimizes for correctness of the recourses and interpretability of the explanations, while minimizing overall recourse costs across the entire population. More specifically, our objective enables us to learn, with optimality guarantees on recourse correctness, a small number of compact rule sets each of which capture recourses for well defined subpopulations within the data. We also demonstrate theoretically that several of the prior approaches proposed to generate recourses for individuals are special cases of our framework. Experimental evaluation with real world datasets and user studies demonstrate that our framework can provide decision makers with a comprehensive overview of recourses corresponding to any black box model, and consequently help detect undesirable model biases and discrimination.

References in corpus (12)

• Towards A Rigorous Science of Interpretable Machine Learning
• Axiomatic Attribution for Deep Networks
• Understanding Black-box Predictions via Influence Functions
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• SmoothGrad: removing noise by adding noise
• Actionable Recourse in Linear Classification
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Interpretability via Model Extraction
• Model-Agnostic Counterfactual Explanations for Consequential Decisions
• Generating Counterfactual and Contrastive Explanations using SHAP

Cited by in corpus (10)

• Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanations
• Counterfactual Shapley Additive Explanations
• Considerations When Learning Additive Explanations for Black-Box Models
• GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
• Achieving Diversity in Counterfactual Explanations: a Review and Discussion
• Setting the Right Expectations: Algorithmic Recourse Over Time
• Rationalizing Predictions by Adversarial Information Calibration
• Framing Algorithmic Recourse for Anomaly Detection
• It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers
• Towards User Guided Actionable Recourse