Poster
in
Workshop: 3rd Workshop on Interpretable Machine Learning in Healthcare (IMLH)

Feature Importance Measurement based on Decision Tree Sampling

CHAO HUANG ⋅ Diptesh Das ⋅ Koji Tsuda

Keywords: Interpretability reliability Decision tree Random Forest SAT Trustworthy AI

Project Page [ OpenReview]

Abstract

Random forest are effective for prediction tasks but the randomness of tree generation hinders interpretability in feature importance analysis. To address this, we proposed a SAT-based method for measuring feature importance in tree-based model. Our method has fewer parameters than random forest and provides higher interpretability and stability for the analysis in real-world problems.

Video

Chat is not available.