4 papers
VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution
Mateusz Gajewski, MikoÅaj Morzy, Adam Karczmarz +1
Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnos…
EXALT: EXplainable ALgorithmic Tools for Optimization Problems
Zuzanna BÄ czek, MichaÅ BizoÅ, Aneta Pawelec +1
Algorithmic solutions have significant potential to improve decision-making across various domains, from healthcare to e-commerce. However, the widespread adoption of these solutio…
Accurate estimation of feature importance faithfulness for tree models
Mateusz Gajewski, Adam Karczmarz, Mateusz Rapicki +1
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-base…
Since Faithfulness Fails: The Performance Limits of Neural Causal Discovery
Mateusz Olko, Mateusz Gajewski, Joanna Wojciechowska +3
Neural causal discovery methods have recently improved in terms of scalability and computational efficiency. However, our systematic evaluation highlights significant room for impr…