English

On Relating 'Why?' and 'Why Not?' Explanations

Machine Learning 2020-12-22 v1 Artificial Intelligence Logic in Computer Science

Abstract

Explanations of Machine Learning (ML) models often address a 'Why?' question. Such explanations can be related with selecting feature-value pairs which are sufficient for the prediction. Recent work has investigated explanations that address a 'Why Not?' question, i.e. finding a change of feature values that guarantee a change of prediction. Given their goals, these two forms of explaining predictions of ML models appear to be mostly unrelated. However, this paper demonstrates otherwise, and establishes a rigorous formal relationship between 'Why?' and 'Why Not?' explanations. Concretely, the paper proves that, for any given instance, 'Why?' explanations are minimal hitting sets of 'Why Not?' explanations and vice-versa. Furthermore, the paper devises novel algorithms for extracting and enumerating both forms of explanations.

Keywords

Cite

@article{arxiv.2012.11067,
  title  = {On Relating 'Why?' and 'Why Not?' Explanations},
  author = {Alexey Ignatiev and Nina Narodytska and Nicholas Asher and Joao Marques-Silva},
  journal= {arXiv preprint arXiv:2012.11067},
  year   = {2020}
}
R2 v1 2026-06-23T21:06:51.878Z