Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End

Abstract

Feature attributions and counterfactual explanations are popular approaches to explain a ML model. The former assigns an importance score to each input feature, while the latter provides input examples with minimal changes to alter the model's predictions. To unify these approaches, we provide an interpretation based on the actual causality framework and present two key results in terms of their use. First, we present a method to generate feature attribution explanations from a set of counterfactual examples. These feature attributions convey how important a feature is to changing the classification outcome of a model, especially on whether a subset of features is necessary and/or sufficient for that change, which attribution-based methods are unable to provide. Second, we show how counterfactual examples can be used to evaluate the goodness of an attribution-based explanation in terms of its necessity and sufficiency. As a result, we highlight the complementarity of these two approaches. Our evaluation on three benchmark datasets - Adult-Income, LendingClub, and German-Credit - confirms the complementarity. Feature attribution methods like LIME and SHAP and counterfactual explanation methods like Wachter et al. and DiCE often do not agree on feature importance rankings. In addition, by restricting the features that can be modified for generating counterfactual examples, we find that the top-k features from LIME or SHAP are often neither necessary nor sufficient explanations of a model's prediction. Finally, we present a case study of different explanation methods on a real-world hospital triage problem

arXiv comment15 pages, 10 figures

References in corpus (9)

• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Questioning the AI: Informing Design Practices for Explainable AI User Experiences
• Actionable Recourse in Linear Classification
• On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detection
• FACE: Feasible and Actionable Counterfactual Explanations
• Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches
• The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
• CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models
• Multi-Objective Counterfactual Explanations

Cited by in corpus (9)

• Denoising diffusion algorithm for inverse design of microstructures with fine-tuned nonlinear material properties
• Counterfactual Shapley Additive Explanations
• A comprehensive interpretable machine learning framework for Mild Cognitive Impairment and Alzheimer's disease diagnosis
• Can counterfactual explanations of AI systems' predictions skew lay users' causal intuitions about the world? If so, can we correct for that?
• IDP-PGFE: An Interpretable Disruption Predictor based on Physics-Guided Feature Extraction
• Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Box
• On the Connection between Game-Theoretic Feature Attributions and Counterfactual Explanations
• A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking
• Robot Pouring: Identifying Causes of Spillage and Selecting Alternative Action Parameters Using Probabilistic Actual Causation