Achieving Diversity in Counterfactual Explanations: a Review and Discussion
arXiv:2305.05840 · doi:10.1145/3593013.3594122
Abstract
In the field of Explainable Artificial Intelligence (XAI), counterfactual examples explain to a user the predictions of a trained decision model by indicating the modifications to be made to the instance so as to change its associated prediction. These counterfactual examples are generally defined as solutions to an optimization problem whose cost function combines several criteria that quantify desiderata for a good explanation meeting user needs. A large variety of such appropriate properties can be considered, as the user needs are generally unknown and differ from one user to another; their selection and formalization is difficult. To circumvent this issue, several approaches propose to generate, rather than a single one, a set of diverse counterfactual examples to explain a prediction. This paper proposes a review of the numerous, sometimes conflicting, definitions that have been proposed for this notion of diversity. It discusses their underlying principles as well as the hypotheses on the user needs they rely on and proposes to categorize them along several dimensions (explicit vs implicit, universe in which they are defined, level at which they apply), leading to the identification of further research challenges on this topic.
References in corpus (25)
- Towards A Rigorous Science of Interpretable Machine Learning
- A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- A Survey on the Explainability of Supervised Machine Learning
- Actionable Recourse in Linear Classification
- FACE: Feasible and Actionable Counterfactual Explanations
- CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models
- Learning Model-Agnostic Counterfactual Explanations for Tabular Data
- Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
- Algorithmic Recourse: from Counterfactual Explanations to Interventions
- Generalized Inverse Classification
- A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Data
- Model-Based Counterfactual Synthesizer for Interpretation
- Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses
- Issues with post-hoc counterfactual explanations: a discussion
- Consequence-aware Sequential Counterfactual Generation
- From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
- Decisions, Counterfactual Explanations and Strategic Behavior
- GeCo: Quality Counterfactual Explanations in Real Time
- MACE: An Efficient Model-Agnostic Framework for Counterfactual Explanation
- Optimal Counterfactual Explanations for Scorecard modelling
- DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement
- Counterfactual Plans under Distributional Ambiguity
- On the Trade-Off between Actionable Explanations and the Right to be Forgotten
- Feasible Recourse Plan via Diverse Interpolation