Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (9) · 11164-11173
DOI: 10.1609/aaai.v37i9.26322 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Artjom Zern und 2 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref).
Abstract (Originalsprache)
In recent years, game-theoretic Shapley values have gained increasing attention with respect to local model explanation by feature attributions. While the approach using Shapley values is model-independent, their (exact) computation is usually intractable, so efficient model-specific algorithms have been devised including approaches for decision trees or their ensembles in general. Our work goes further in this direction by extending the interventional TreeSHAP algorithm to piecewise linear regression trees, which gained more attention in the past few years. To this end, we introduce a decomposition of the contribution function based on decision paths, which allows a more comprehensible formulation of SHAP algorithms for tree-based models. Our algorithm can also be readily applied to computing SHAP interaction values of these models. In particular, as the main contribution of this paper, we provide a more efficient approach of interventional SHAP for tree-based models by precomputing statistics of the background data based on the tree structure.
Zitieren
APA
Zern, A., Broelemann, K., & Kasneci, G. (2023). Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees. Proceedings of the AAAI Conference on Artificial Intelligence, 37(9), 11164-11173. https://doi.org/10.1609/aaai.v37i9.26322
Vancouver
Zern A, Broelemann K, Kasneci G. Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(9):11164-11173. doi:10.1609/aaai.v37i9.26322
BibTeX
@article{Zern2023,
author = {Zern, Artjom and Broelemann, Klaus and Kasneci, Gjergji},
title = {Interventional SHAP Values and Interaction Values for Piecewise Linear Regression Trees},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {9},
pages = {11164--11173},
doi = {10.1609/aaai.v37i9.26322}
}
EUVIMED