Accurate Estimation of Feature Importance Faithfulness for Tree Models
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.
Cite
Text
Gajewski et al. "Accurate Estimation of Feature Importance Faithfulness for Tree Models." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I16.33834Markdown
[Gajewski et al. "Accurate Estimation of Feature Importance Faithfulness for Tree Models." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/gajewski2025aaai-accurate/) doi:10.1609/AAAI.V39I16.33834BibTeX
@inproceedings{gajewski2025aaai-accurate,
title = {{Accurate Estimation of Feature Importance Faithfulness for Tree Models}},
author = {Gajewski, Mateusz and Karczmarz, Adam and Rapicki, Mateusz and Sankowski, Piotr},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2025},
pages = {16691-16698},
doi = {10.1609/AAAI.V39I16.33834},
url = {https://mlanthology.org/aaai/2025/gajewski2025aaai-accurate/}
}