Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Muschalik, Maximilian, Fumagalli, Fabian, Hammer, Barbara, Hüllermeier, Eyke
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913397717598208
author Muschalik, Maximilian
Fumagalli, Fabian
Hammer, Barbara
Hüllermeier, Eyke
author_facet Muschalik, Maximilian
Fumagalli, Fabian
Hammer, Barbara
Hüllermeier, Eyke
contents While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the Shapley value (SV) is a well-known concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. The model-specific TreeSHAP methodology solves the exponential complexity for retrieving exact SVs from tree-based models. Expanding beyond individual feature attribution, Shapley interactions reveal the impact of intricate feature interactions of any order. In this work, we present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions of tree-based models. TreeSHAP-IQ is supported by a mathematical framework that exploits polynomial arithmetic to compute the interaction scores in a single recursive traversal of the tree, akin to Linear TreeSHAP. We apply TreeSHAP-IQ on state-of-the-art tree ensembles and explore interactions on well-established benchmark datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2401_12069
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
Muschalik, Maximilian
Fumagalli, Fabian
Hammer, Barbara
Hüllermeier, Eyke
Machine Learning
While shallow decision trees may be interpretable, larger ensemble models like gradient-boosted trees, which often set the state of the art in machine learning problems involving tabular data, still remain black box models. As a remedy, the Shapley value (SV) is a well-known concept in explainable artificial intelligence (XAI) research for quantifying additive feature attributions of predictions. The model-specific TreeSHAP methodology solves the exponential complexity for retrieving exact SVs from tree-based models. Expanding beyond individual feature attribution, Shapley interactions reveal the impact of intricate feature interactions of any order. In this work, we present TreeSHAP-IQ, an efficient method to compute any-order additive Shapley interactions for predictions of tree-based models. TreeSHAP-IQ is supported by a mathematical framework that exploits polynomial arithmetic to compute the interaction scores in a single recursive traversal of the tree, akin to Linear TreeSHAP. We apply TreeSHAP-IQ on state-of-the-art tree ensembles and explore interactions on well-established benchmark datasets.
title Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
topic Machine Learning
url https://arxiv.org/abs/2401.12069