Title
Accurate estimation of feature importance faithfulness for tree models
Authors
[ 1 ] Wydział Informatyki i Telekomunikacji, Politechnika Poznańska | [ SzD ] doctoral school student
Scientific discipline (Law 2.0)
Year of publication
2025
Chapter type
chapter in monograph / paper
Publication language
english
Keywords
EN
- explainability
- explainable machine learning
- tree models
Abstract
EN 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.
Date of online publication
11.04.2025
Pages (from - to)
16691 - 16698
Comments
Vol. 39, No. 16: AAAI-25 Technical Tracks 16
Ministry points / chapter
5
Ministry points / conference (CORE)
200
System created by Poznań University of Technology
and Poznan Supercomputing and Networking Center
Log in through eKonto to add to SIS