3 papers
cs.LG2026
Fair Feature Importance Scores via Feature Occlusion and Permutation
Camille Little, Madeline Navarro, Santiago Segarra +1
As machine learning models increasingly impact society, their opaque nature poses challenges to trust and accountability, particularly in fairness contexts. Understanding how indiv…
cs.LG2025
Top- Feature Importance Ranking
Yuxi Chen, Tiffany Tang, Genevera Allen
Accurate ranking of important features is a fundamental challenge in interpretable machine learning with critical applications in scientific discovery and decision-making. Unlike f…
stat.ML2025
iLOCO: Distribution-Free Inference for Feature Interactions
Camille Little, Lili Zheng, Genevera Allen
Feature importance measures are widely studied and are essential for understanding model behavior, guiding feature selection, and enhancing interpretability. However, many machine…