Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

FACE: Feasible and Actionable Counterfactual Explanations

About

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.

Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez, Tijl De Bie, Peter Flach• 2019

Related benchmarks

TaskDatasetResultRank
Counterfactual ExplanationsCOMPAS
Validity42.7
21
Counterfactual ExplanationsCancer
Validity35.7
15
Counterfactual ExplanationsDiabetes
Validity44.5
15
Counterfactual ExplanationsFICO
Validity43
15
Counterfactual ExplanationsHousing
Validity36.5
15
Counterfactual ExplanationsTitanic
Validity44.7
14
Counterfactual ExplanationsBank
Validity39.4
14
Counterfactual ExplanationsHome
Validity34.1
10
Algorithmic RecourseAustralian Credit
Validity100
10
Algorithmic RecourseDiabetes
Validity100
10
Showing 10 of 13 rows

Other info

Follow for update