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

Muschalik, Maximilian ; Fumagalli, Fabian ; Hammer, Barbara und Hüllermeier, Eyke (Februar 2024): Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles. AAAI Conference on Artificial Intelligence 2024, Vancouver, Canada, 20-27 February 2024. Proceedings of the AAAI Conference on Artificial Intelligence. Bd. 38, Nr. 13 S. 14388-14396

Abstract

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.

• Dokumententyp: Konferenzbeitrag (Paper)
• Fakultät: Mathematik, Informatik und Statistik > Informatik > Künstliche Intelligenz und Maschinelles Lernen
• Themengebiete: 000 Informatik, Informationswissenschaft, allgemeine Werke > 004 Informatik
• ISSN: 2159-5399
• Sprache: Englisch
• DFG: Gefördert durch die Deutsche Forschungsgemeinschaft (DFG) - 438445824