arXiv:2606. 15273v1 Announce Type: new Abstract: Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided.
arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.
arXiv:2607. 16236v1 Announce Type: cross Abstract: Explainability methods for time series models predominantly produce flat attribution scores: they quantify the direct influence of a feature at a timestamp by a scalar.
arXiv:2608. 03772v1 Announce Type: new Abstract: Explaining the predictions of neural networks is a central challenge in trustworthy AI.
arXiv:2608. 03868v1 Announce Type: cross Abstract: Causal Discovery (CD) from observational data faces two fundamental challenges.
arXiv:2607. 11510v1 Announce Type: new Abstract: Causal discovery from observational tabular data remains fundamentally challenging, primarily due to the heterogeneity of underlying causal mechanisms and the high-dimensional combinatorial search space of Directed Acyclic Graphs (DAGs).
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
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: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.
The paper introduces Cluster-DAGs as a flexible prior knowledge framework to improve causal discovery. It presents two modified constraint‑based algorithms, Cluster‑PC and Cluster‑FCI, tailored for fully and partially observed data. Experiments on simulated data show that these methods outperform baseline algorithms that lack prior knowledge.
arXiv:2601. 16249v3 Announce Type: replace-cross Abstract: Learning DAG structures from purely observational data remains a long-standing challenge across scientific domains.
arXiv:2606. 03251v1 Announce Type: new Abstract: In nature, events that affect some individuals or groups but not others constitute an implicit intervention and are known as natural experiments.
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.