The paper proposes a new evaluation test for explanation methods: if an explanation accurately captures how a model uses its features, one should be able to reconstruct the model’s predictions from it. The authors convert explanations into predictors by summing feature effects and assess how well these predictors reproduce the model on unseen data, without any fitting. They apply this test to partial dependence plots, accumulated local effects, SHAP, and LIME across multiple datasets and model families, showing that the best method depends on feature dependence and that some existing quality metrics can favor flawed explanations.
By Jacob Selb{\ae}k, Hugo L. Hammer
Inherently interpretable classifiers for tabular data typically rely on sparse features, rules, or patterns that users can inspect directly. The marginal feature-screening step common to these methods can discard variables whose predictive value emerges only through joint configurations with other variables.
arXiv:2603. 02221v2 Announce Type: replace-cross Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods.
By Zizheng Zhang, Yiming Li, Justin Xu, Jinyu Wang, Rui Wang, Lei Song, Jiang Bian, David W Eyre, Jingjing Fu
The paper introduces a straightforward evaluation method for explanation techniques: by converting each explanation into a predictor that sums the feature effects, the authors assess how accurately this predictor reproduces the original model’s predictions on unseen data. This approach applies to any explanation expressible as a function of features and is demonstrated on PDP, ALE, SHAP, and LIME. The authors theoretically show that summing partial dependence curves yields the optimal additive summary when features are independent, but this property fails with dependent features, and empirical results across diverse datasets confirm that the best-performing method depends on feature dependence.
arXiv:2607. 07060v1 Announce Type: cross Abstract: Inherently interpretable classifiers for tabular data typically rely on sparse features, rules, or patterns that users can inspect directly.
By Srikumar Krishnamoorthy
arXiv:2607. 27463v1 Announce Type: new Abstract: Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning models, and assisting in the explanation of complex opaque models.
By Lucas Greff Meneses, Evandro S. Ortigossa, Claudio Silva, Luis Gustavo Nonato