Explanations for Monotonic Classifiers
Machine Learning
2021-06-02 v1 Machine Learning
Abstract
In many classification tasks there is a requirement of monotonicity. Concretely, if all else remains constant, increasing (resp. decreasing) the value of one or more features must not decrease (resp. increase) the value of the prediction. Despite comprehensive efforts on learning monotonic classifiers, dedicated approaches for explaining monotonic classifiers are scarce and classifier-specific. This paper describes novel algorithms for the computation of one formal explanation of a (black-box) monotonic classifier. These novel algorithms are polynomial in the run time complexity of the classifier and the number of features. Furthermore, the paper presents a practically efficient model-agnostic algorithm for enumerating formal explanations.
Cite
@article{arxiv.2106.00154,
title = {Explanations for Monotonic Classifiers},
author = {Joao Marques-Silva and Thomas Gerspacher and Martin Cooper and Alexey Ignatiev and Nina Narodytska},
journal= {arXiv preprint arXiv:2106.00154},
year = {2021}
}