Explaining Black-Box Models through Counterfactuals

Title

Explaining Black-Box Models through Counterfactuals

 Author

Altmeyer, P. (TU Delft Multimedia Computing) ORCID 0000-0003-4726-8613
Liem, C.C.S. (TU Delft Multimedia Computing) ORCID 0000-0002-5385-7695
van Deursen, A. (TU Delft Software Technology) ORCID 0000-0003-4850-3312

 Department

Software Technology

 Date

2023

 Abstract

We present CounterfactualExplanations.jl: a package for generating Counterfactual Explanations (CE) and Algorithmic Recourse (AR) for black-box models in Julia. CE explain how inputs into a model need to change to yield specific model predictions. Explanations that involve realistic and actionable changes can be used to provide AR: a set of proposed actions for individuals to change an undesirable outcome for the better. In this article, we discuss the usefulness of CE for Explainable Artificial Intelligence and demonstrate the functionality of our package. The package is straightforward to use and designed with a focus on customization and extensibility. We envision it to one day be the go-to place for explaining arbitrary predictive models in Julia through a diverse suite of counterfactual generators.

 Subject

Julia
Explainable AI
Counterfactual Explanations
Algorithmic Recourse

 To reference this document use:

http://resolver.tudelft.nl/uuid:446dc879-2782-4f89-9e25-120e912448ae

 DOI

https://doi.org/10.21105/jcon.00130

 Source

The Proceedings of the JuliaCon Conferences (JCON)

 Part of collection

Institutional Repository

 Document type

conference paper

 Rights

© 2023 P. Altmeyer, C.C.S. Liem, A. van Deursen
Files
PDF 10.21105.jcon.00130.pdf 901.19 KB
Close viewer