Explaining Black-Box Models through Counterfactuals
arXiv:2308.07198 · doi:10.21105/jcon.00130
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.
arXiv comment13 pages, 9 figures, originally published in The Proceedings of the JuliaCon Conferences (JCON)
References in corpus (7)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Actionable Recourse in Linear Classification
- Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
- MLJ: A Julia package for composable machine learning
- Inverse Classification for Comparison-based Interpretability in Machine Learning
- Endogenous Macrodynamics in Algorithmic Recourse