The paper introduces an imprecise Dirichlet model (IDM) approach to evaluate the robustness of Shapley values in tree-based models such as decision trees and random forests. By quantifying interval-valued Shapley values—using pessimistic and averaging principles—when a few unannotated instances are added to tree leaves, the authors derive efficient computational methods and extend the framework to Banzhaf values. Experiments and case studies demonstrate how these interval-valued explanations can be applied to debias uninformative features.
arXiv:2410. 01917v3 Announce Type: replace-cross Abstract: Originally introduced in game theory, Shapley values have emerged as a central tool in explainable machine learning, where they are used to attribute model predictions to specific input features.
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.
arXiv:2608.24104v1 Announce Type: cross Abstract: Numerous methods have been developed to quantify feature attributions in individual predictions for tree ensembles. However, many applications requir...
arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.
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.
arXiv:2604. 15107v2 Announce Type: replace-cross Abstract: Shapley values provide a flexible framework for attributing feature contributions to model predictions, but they are not naturally suited for feature selection: a feature may receive a positive attribution even when it is redundant given the remaining variables.
arXiv:2408. 01382v3 Announce Type: replace Abstract: Originating in game theory, Shapley values are widely used for explaining a machine learning model's prediction by quantifying the contribution of each feature's value to the prediction.
arXiv:2608. 08078v1 Announce Type: new Abstract: Interval prediction aims to achieve a target coverage level while producing intervals that are as short as possible.
The paper introduces techniques for measuring the robustness of predictions made by two generative classifiers—naive Bayes classifiers and generative forests—whose underlying models are probabilistic graphical models. Robustness is defined as the degree to which the classifier’s distribution can be perturbed without altering its prediction, with perturbations explored via epsilon‑contamination, total variation distance, and chi‑squared divergence neighborhoods. Experiments on benchmark datasets show that the computed robustness values can serve as indicators of prediction trustworthiness and are compared against other existing indicators.
arXiv:2607. 03675v1 Announce Type: new Abstract: Shapley values are widely used to attribute value to training data based on their marginal contribution to performance on a validation set.
arXiv:2608. 04310v1 Announce Type: new Abstract: The Rashomon effect describes the phenomenon that many models can achieve nearly equivalent performance on the same learning task, with significant ramifications for robustness, feature importance, and customizability.
The paper develops an explanatory framework for weighted naive Bayes classifiers by transforming the traditional supervised distance based on conditional log-likelihoods into a discriminative log‑odds representation. It demonstrates that this new representation yields a distance identical to the α1 distance between vectors of analytical Shapley values, thereby linking model geometry to local explanations. The authors also empirically evaluate various supervised distances derived from these representations using a k‑nearest neighbors classifier.