arXiv:2607. 14096v1 Announce Type: new Abstract: In predictive modeling, the ability to explain why a model produces a given target prediction has become increasingly important [5, 10].
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.
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:2601.06701v2 Announce Type: replace-cross Abstract: Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Comm...
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.
arXiv:2603. 13326v2 Announce Type: replace-cross Abstract: Multimodal Transformers often produce predictions without clarifying how different modalities jointly support a decision.
arXiv:2606. 14245v1 Announce Type: new Abstract: Drug-target interaction (DTI) and affinity (DTA) predictors increasingly achieve strong benchmark scores, yet their internal use of sequence, fingerprint, and graph features often remains opaque.
The paper introduces Adaptive Derivative-Ordered Random Explanation (ADORE), a unified framework that uses first- and second-order derivatives to capture nonlinear feature interactions and feature-sample dynamics. ADORE combines global feature importance with local sample contributions, quantifying both magnitude and direction of feature impact while identifying critical samples. It achieves computational efficiency via randomized SVD and dynamic sparsity detection, outperforming LIME and SHAP across tabular, text, and image data, and is released as an open-source Python package on GitHub.
arXiv:2512. 11081v2 Announce Type: replace-cross Abstract: Feature and Interaction Importance (FII) methods are essential in supervised learning for assessing the relevance of input variables and their interactions in complex prediction models.
arXiv:2610.01641v1 Announce Type: cross Abstract: Modern machine-learning models often contain strongly dependent or redundant features, making feature attribution difficult because shared predictive...
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
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.
The paper refactors and expands the scikit-rebate Python package, adding new Relief‑Based Algorithm (RBA) variants such as SWRF*, mu‑Relief, and five novel methods that use alternative neighbor selection and feature scoring strategies. Benchmarking across diverse genomic simulations shows that most RBAs, except mu‑Relief, effectively detect 2‑way interactions in noisy data, with far‑scoring variants like MultiSWRFDB* excelling at interaction detection but being less sensitive to main effects. The refactored package achieves 10‑ to 35‑fold runtime reductions, and the new RBAs maintain strong performance for both main effects and 2‑way epistatic interactions, preserving predictive signals for downstream modeling.