English

Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models

Machine Learning 2022-10-17 v2 Machine Learning

Abstract

To explain the decision of any model, we extend the notion of probabilistic Sufficient Explanations (P-SE). For each instance, this approach selects the minimal subset of features that is sufficient to yield the same prediction with high probability, while removing other features. The crux of P-SE is to compute the conditional probability of maintaining the same prediction. Therefore, we introduce an accurate and fast estimator of this probability via random Forests for any data (X,Y)(\boldsymbol{X}, Y) and show its efficiency through a theoretical analysis of its consistency. As a consequence, we extend the P-SE to regression problems. In addition, we deal with non-discrete features, without learning the distribution of X\boldsymbol{X} nor having the model for making predictions. Finally, we introduce local rule-based explanations for regression/classification based on the P-SE and compare our approaches w.r.t other explainable AI methods. These methods are available as a Python package at \url{www.github.com/salimamoukou/acv00}.

Keywords

Cite

@article{arxiv.2111.04658,
  title  = {Consistent Sufficient Explanations and Minimal Local Rules for explaining regression and classification models},
  author = {Salim I. Amoukou and Nicolas J. B Brunel},
  journal= {arXiv preprint arXiv:2111.04658},
  year   = {2022}
}

Comments

Accepted at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

R2 v1 2026-06-24T07:31:00.314Z