Navigating Explanatory Multiverse Through Counterfactual Path Geometry
arXiv:2306.02786 · doi:10.1007/s10994-025-06769-2
Abstract
Counterfactual explanations are the de facto standard when tasked with interpreting decisions of (opaque) predictive models. Their generation is often subject to technical and domain-specific constraints that aim to maximise their real-life utility. In addition to considering desiderata pertaining to the counterfactual instance itself, guaranteeing existence of a viable path connecting it with the factual data point has recently gained relevance. While current explainability approaches ensure that the steps of such a journey as well as its destination adhere to selected constraints, they neglect the multiplicity of these counterfactual paths. To address this shortcoming we introduce the novel concept of explanatory multiverse that encompasses all the possible counterfactual journeys. We define it using vector spaces, showing how to navigate, reason about and compare the geometry of counterfactual trajectories found within it. To this end, we overview their spatial properties -- such as affinity, branching, divergence and possible future convergence -- and propose an all-in-one metric, called opportunity potential, to quantify them. Notably, the explanatory process offered by our method grants explainees more agency by allowing them to select counterfactuals not only based on their absolute differences but also according to the properties of their connecting paths. To demonstrate real-life flexibility, benefit and efficacy of explanatory multiverse we propose its graph-based implementation, which we use for qualitative and quantitative evaluation on six tabular and image data sets.
ECML-PKDD 2025: Journal Track (Springer Machine Learning) & ICML 2023 Workshop on Counterfactuals in Minds and Machines
References in corpus (19)
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Actionable Recourse in Linear Classification
- MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
- 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
- One Explanation Does Not Fit All: The Promise of Interactive Explanations for Machine Learning Transparency
- Learning Model-Agnostic Counterfactual Explanations for Tabular Data
- Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
- Model-Agnostic Counterfactual Explanations for Consequential Decisions
- What Does Evaluation of Explainable Artificial Intelligence Actually Tell Us? A Case for Compositional and Contextual Validation of XAI Building Blocks
- Impact Of Explainable AI On Cognitive Load: Insights From An Empirical Study
- Achieving Diversity in Counterfactual Explanations: a Review and Discussion
- Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse
- Comprehension Is a Double-Edged Sword: Over-Interpreting Unspecified Information in Intelligible Machine Learning Explanations
- LIMEtree: Consistent and Faithful Surrogate Explanations of Multiple Classes
- The Importance of Time in Causal Algorithmic Recourse
- Helpful, Misleading or Confusing: How Humans Perceive Fundamental Building Blocks of Artificial Intelligence Explanations
- TraCE: Trajectory Counterfactual Explanation Scores