← Search

Mateusz Gajewski

2 accepted papers

2025

Accurate Estimation of Feature Importance Faithfulness for Tree Models

AAAI 2025technical

In this paper, we consider a perturbation-based metric of predictive faithfulness of feature rankings (or attributions) that we call PGI squared When applied to decision tree-based regression models, the metric can be computed exactly and efficiently for arbitrary independent feature pertu…

2025

Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery

ICML 2025poster

Neural causal discovery methods have recently improved in terms of scalability and computational efficiency. However, our systematic evaluation highlights significant room for improvement in their accuracy when uncovering causal structures. We identify a fundamental limitation: \textit{unavoidable…

Cited by 0SourcePDFScholar