Global Counterfactual Explanations: Investigations, Implementations and Improvements

TL;DR

This paper investigates global counterfactual explanations, focusing on implementing and improving Actionable Recourse Summaries (AReS), to provide more reliable, scalable, and interactive explainability tools beyond local explanations.

Contribution

It offers an in-depth analysis of existing global methods and introduces enhancements to the AReS framework for better global counterfactual explanations.

Findings

Enhanced AReS framework for improved global explanations

Demonstrated scalability and efficiency of the proposed methods

Provided insights into the limitations of local explanation aggregation

Abstract

Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are requesting more efficient and interactive explainability tools. We take this opportunity to investigate existing global methods, with a focus on implementing and improving Actionable Recourse Summaries (AReS), the only known global counterfactual explanation framework for recourse.