Accurate Estimation of Feature Importance Faithfulness for Tree Models
Open Access
- 11 April 2025
- journal article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (16) , 16691-16698
Abstract
In this paper, we consider a perturbation-based metric of predictive faithfulness of feature rankings (or attributions) that we call PGI squared When applied to decision tree-based regression models, the metric can be computed exactly and efficiently for arbitrary independent feature perturbation distributions. In particular, the computation does not involve Monte Carlo sampling that has been typically used for computing similar metrics and which is inherently prone to inaccuracies. As a second contribution, we proposed a procedure for constructing feature ranking based on PGI squared. Our results indicate the proposed ranking method is comparable to the widely recognized SHAP explainer, offering a viable alternative for assessing feature importance in tree-based models.Keywords
All Related Versions
This publication has 2 references indexed in Scilit:
- A Survey on the Explainability of Supervised Machine LearningJournal of Artificial Intelligence Research, 2021
- From local explanations to global understanding with explainable AI for treesNature Machine Intelligence, 2020