{"type":"conference","department":[{"_id":"660"}],"date_created":"2025-01-16T16:12:16Z","abstract":[{"text":"The Shapley value (SV) is a prevalent approach of allocating credit to machine learning (ML) entities to understand black box ML models. Enriching such interpretations with higher-order interactions is inevitable for complex systems, where the Shapley Interaction Index (SII) is a direct axiomatic extension of the SV. While it is well-known that the SV yields an optimal approximation of any game via a weighted least square (WLS) objective, an extension of this result to SII has been a long-standing open problem, which even led to the proposal of an alternative index. In this work, we characterize higher-order SII as a solution to a WLS problem, which constructs an optimal approximation via SII and k-Shapley values (k-SII). We prove this representation for the SV and pairwise SII and give empirically validated conjectures for higher orders. As a result, we propose KernelSHAP-IQ, a direct extension of KernelSHAP for SII, and demonstrate state-of-the-art performance for feature interactions.","lang":"eng"}],"project":[{"_id":"109","name":"TRR 318: TRR 318 - Erklärbarkeit konstruieren"},{"name":"TRR 318 - C: TRR 318 - Project Area C","_id":"117"},{"name":"TRR 318 - C3: TRR 318 - Subproject C3","_id":"126"}],"publication":"Proceedings of the 41st International Conference on Machine Learning (ICML)","citation":{"mla":"Fumagalli, Fabian, et al. “KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions.” Proceedings of the 41st International Conference on Machine Learning (ICML), vol. 235, PMLR, 2024, pp. 14308–14342.","ama":"Fumagalli F, Muschalik M, Kolpaczki P, Hüllermeier E, Hammer B. KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions. In: Proceedings of the 41st International Conference on Machine Learning (ICML). Vol 235. Proceedings of Machine Learning Research. PMLR; 2024:14308–14342.","bibtex":"@inproceedings{Fumagalli_Muschalik_Kolpaczki_Hüllermeier_Hammer_2024, series={Proceedings of Machine Learning Research}, title={KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions}, volume={235}, booktitle={Proceedings of the 41st International Conference on Machine Learning (ICML)}, publisher={PMLR}, author={Fumagalli, Fabian and Muschalik, Maximilian and Kolpaczki, Patrick and Hüllermeier, Eyke and Hammer, Barbara}, year={2024}, pages={14308–14342}, collection={Proceedings of Machine Learning Research} }","apa":"Fumagalli, F., Muschalik, M., Kolpaczki, P., Hüllermeier, E., & Hammer, B. (2024). KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions. Proceedings of the 41st International Conference on Machine Learning (ICML), 235, 14308–14342.","ieee":"F. Fumagalli, M. Muschalik, P. Kolpaczki, E. Hüllermeier, and B. Hammer, “KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions,” in Proceedings of the 41st International Conference on Machine Learning (ICML), 2024, vol. 235, pp. 14308–14342.","short":"F. Fumagalli, M. Muschalik, P. Kolpaczki, E. Hüllermeier, B. Hammer, in: Proceedings of the 41st International Conference on Machine Learning (ICML), PMLR, 2024, pp. 14308–14342.","chicago":"Fumagalli, Fabian, Maximilian Muschalik, Patrick Kolpaczki, Eyke Hüllermeier, and Barbara Hammer. “KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions.” In Proceedings of the 41st International Conference on Machine Learning (ICML), 235:14308–14342. Proceedings of Machine Learning Research. PMLR, 2024."},"user_id":"93420","volume":235,"page":"14308–14342","series_title":"Proceedings of Machine Learning Research","_id":"58223","publisher":"PMLR","language":[{"iso":"eng"}],"date_updated":"2025-09-11T16:27:05Z","intvolume":" 235","year":"2024","title":"KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions","status":"public","author":[{"full_name":"Fumagalli, Fabian","first_name":"Fabian","last_name":"Fumagalli"},{"first_name":"Maximilian","last_name":"Muschalik","full_name":"Muschalik, Maximilian"},{"last_name":"Kolpaczki","first_name":"Patrick","full_name":"Kolpaczki, Patrick"},{"last_name":"Hüllermeier","first_name":"Eyke","full_name":"Hüllermeier, Eyke"},{"first_name":"Barbara","last_name":"Hammer","full_name":"Hammer, Barbara"}]}