The paper introduces a novel method that merges Monte Carlo sampling with linear regression to estimate probabilistic values such as Shapley and Banzhaf values. It generalizes previous algorithms by allowing any efficiently computable function family, enabling the use of tree-based models like XGBoost and cross‑fitting for unbiased estimates. Experiments on eight datasets show the approach achieves state‑of‑the‑art accuracy, reducing error by up to 11× for Shapley values and 390× for general probabilistic values compared to existing methods.
By R. Teal Witter, Yurong Liu, Christopher Musco
arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.
By Seungeun Lee, Joao Fonseca, Julia Stoyanovich
arXiv:2606. 02247v1 Announce Type: cross Abstract: Shapley values are a principled attribution measure widely used in interpretable machine learning, but their exact computation scales exponentially with the number of players, motivating a wide range of approximation methods based on value function evaluations of sampled coalitions.
By David Rundel, Fabian Fumagalli, Maximilian Muschalik, Bernd Bischl, Matthias Feurer
arXiv:2611.07173v1 Announce Type: cross
Abstract: Shapley values are a central tool for attribution in machine learning. Since their exact computation requires evaluating the cooperative game to be e...
By David Rundel, R. Teal Witter, Santo M. A. R. Thies, Matthias Feurer, Fabian Fumagalli, Bernd Bischl
arXiv:2603. 03672v2 Announce Type: replace Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space.
By Xuan Yang, Hsi-Wen Chen, Ming-Syan Chen, Jian Pei
arXiv:2510. 22138v3 Announce Type: replace Abstract: We show how to replace the O(2^n) coalition enumeration over n features behind Shapley values and Shapley-style interaction indices with a few-evaluation scheme on a tensor-network (TN) surrogate: TN-SHAP.
By Farzaneh Heidari, Chao Li, Guillaume Rabusseau
arXiv:2508. 07952v2 Announce Type: replace Abstract: Clustering algorithms often assume all features contribute equally to the data structure, an assumption that usually fails in high-dimensional or noisy settings.
By Richard J. Fawley, Renato Cordeiro de Amorim
The paper investigates the phenomenon of explanation multiplicity in SHAP, showing that SHAP explanations can vary significantly across repeated runs even when the model, input, and prediction remain unchanged. The authors introduce a dual‑seed evaluation protocol, a hierarchy of metrics, and null models to quantify this variability, finding that multiplicity is widespread across datasets, models, and sampling strategies. They also demonstrate that common metrics like L2 distance may underestimate instability, while rank‑based metrics reveal substantial changes in top‑ranked features, and that improved sampling methods do not fully eliminate run‑to‑run variation.
By Hyunseung Hwang, Seungeun Lee, Lucas Rosenblatt, Steven Euijong Whang, Julia Stoyanovich
arXiv:2605.02827v2 Announce Type: replace
Abstract: Probabilistic values, including Shapley values and semivalues, provide a model-agnostic framework to attribute the behavior of a black-box model to...
By Ziqi Liu, Kiljae Lee, Yuan Zhang, Weijing Tang
arXiv:2607. 11956v1 Announce Type: cross Abstract: Data Shapley is the standard principled answer to which training points are worth what, and its k-nearest-neighbor (KNN) specialization is the version deployed in practice: the exact estimator shipped by toolkits such as pyDVL and OpenDataVal.
By Zongye Lyu
arXiv:2603. 14014v2 Announce Type: replace Abstract: We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features.
By Adam Belahcen, St\'ephane Mussard
arXiv:2604. 08438v2 Announce Type: replace Abstract: The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems.
By Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low