FACE: Feasible and Actionable Counterfactual Explanations

Abstract

Work in Counterfactual Explanations tends to focus on the principle of "the closest possible world" that identifies small changes leading to the desired outcome. In this paper we argue that while this approach might initially seem intuitively appealing it exhibits shortcomings not addressed in the current literature. First, a counterfactual example generated by the state-of-the-art systems is not necessarily representative of the underlying data distribution, and may therefore prescribe unachievable goals(e.g., an unsuccessful life insurance applicant with severe disability may be advised to do more sports). Secondly, the counterfactuals may not be based on a "feasible path" between the current state of the subject and the suggested one, making actionable recourse infeasible (e.g., low-skilled unsuccessful mortgage applicants may be told to double their salary, which may be hard without first increasing their skill level). These two shortcomings may render counterfactual explanations impractical and sometimes outright offensive. To address these two major flaws, first of all, we propose a new line of Counterfactual Explanations research aimed at providing actionable and feasible paths to transform a selected instance into one that meets a certain goal. Secondly, we propose FACE: an algorithmically sound way of uncovering these "feasible paths" based on the shortest path distances defined via density-weighted metrics. Our approach generates counterfactuals that are coherent with the underlying data distribution and supported by the "feasible paths" of change, which are achievable and can be tailored to the problem at hand.

Presented at AAAI/ACM Conference on AI, Ethics, and Society 2020

References in corpus (1)

• Actionable Recourse in Linear Classification

Cited by in corpus (37)

• A Survey on the Explainability of Supervised Machine Learning
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• Multi-Objective Counterfactual Explanations
• One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
• A Prescriptive Learning Analytics Framework: Beyond Predictive Modelling and onto Explainable AI with Prescriptive Analytics and ChatGPT
• Counterfactual Explanations for Machine Learning on Multivariate Time Series Data
• Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End
• Explainable Machine Learning for Public Policy: Use Cases, Gaps, and Research Directions
• Counterfactual Shapley Additive Explanations
• ReLAX: Reinforcement Learning Agent eXplainer for Arbitrary Predictive Models
• Generating collective counterfactual explanations in score-based classification via mathematical optimization
• Improving Visualization Interpretation Using Counterfactuals
• HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks
• Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Setting
• Rational Shapley Values
• CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models
• Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
• Consequence-aware Sequential Counterfactual Generation
• FAT Forensics: A Python Toolbox for Algorithmic Fairness, Accountability and Transparency
• Achieving Diversity in Counterfactual Explanations: a Review and Discussion
• Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
• Exploiting Preference Elicitation in Interactive and User-centered Algorithmic Recourse: An Initial Exploration
• LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
• On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
• The Intriguing Relation Between Counterfactual Explanations and Adversarial Examples
• People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AI
• Investigating Imperceptibility of Adversarial Attacks on Tabular Data: An Empirical Analysis
• Enhancing Counterfactual Explanation Search with Diffusion Distance and Directional Coherence
• Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Change
• Navigating Explanatory Multiverse Through Counterfactual Path Geometry
• Towards Feasible Counterfactual Explanations: A Taxonomy Guided Template-based NLG Method
• Towards User Guided Actionable Recourse
• SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies
• Perfect Counterfactuals in Imperfect Worlds: Modelling Noisy Implementation of Actions in Sequential Algorithmic Recourse
• Explainability Requirements as Hyperproperties
• Beyond Satisfaction: From Placebic to Actionable Explanations For Enhanced Understandability
• Realistic Counterfactual Explanations via Denial Constraints