Skip to content

FACE: Feasible and Actionable Counterfactual Explanations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publicationAIES '20
Subtitle of host publicationProceedings of the AAAI/ACM Conference on AI, Ethics, and Society
Publisher or commissioning bodyAssociation for Computing Machinery (ACM)
Pages344-350
Number of pages7
ISBN (Electronic)978-1-4503-7110-0
DOIs
DateAccepted/In press - 6 Dec 2019
DatePublished (current) - 1 Feb 2020

Abstract

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.

Download statistics

No data available

Documents

Documents

  • Full-text PDF (accepted author manuscript)

    Rights statement: This is the author accepted manuscript (AAM). The final published version (version of record) is available online via ACM at https://dl.acm.org/doi/10.1145/3375627.3375850. Please refer to any applicable terms of use of the publisher.

    Accepted author manuscript, 6.63 MB, PDF document

DOI

View research connections

Related faculties, schools or groups