2 papers
cs.LG2026
Local MDI+: Local Feature Importances for Tree-Based Models
Zhongyuan Liang, Zachary T. Rewolinski, Abhineet Agarwal +2
Tree-based ensembles such as random forests remain the go-to for tabular data over deep learning models due to their prediction performance and computational efficiency. These adva…
cs.LG2025
Adaptive Test-Time Intervention for Concept Bottleneck Models
Matthew Shen, Aliyah Hsu, Abhineet Agarwal +1
Concept bottleneck models (CBM) aim to improve model interpretability by predicting human level "concepts" in a bottleneck within a deep learning model architecture. However, how t…