ControlBurn: Feature Selection by Sparse Forests

Abstract

Tree ensembles distribute feature importance evenly amongst groups of correlated features. The average feature ranking of the correlated group is suppressed, which reduces interpretability and complicates feature selection. In this paper we present ControlBurn, a feature selection algorithm that uses a weighted LASSO-based feature selection method to prune unnecessary features from tree ensembles, just as low-intensity fire reduces overgrown vegetation. Like the linear LASSO, ControlBurn assigns all the feature importance of a correlated group of features to a single feature. Moreover, the algorithm is efficient and only requires a single training iteration to run, unlike iterative wrapper-based feature selection methods. We show that ControlBurn performs substantially better than feature selection methods with comparable computational costs on datasets with correlated features.

15 pages

References in corpus (8)

• Scikit-learn: Machine Learning in Python
• XGBoost: A Scalable Tree Boosting System
• A Unified Approach to Interpreting Model Predictions
• CVXPY: A Python-Embedded Modeling Language for Convex Optimization
• InterpretML: A Unified Framework for Machine Learning Interpretability
• S-LIME: Stabilized-LIME for Model Explanation
• Trees, forests, and impurity-based variable importance
• Unbiased Measurement of Feature Importance in Tree-Based Methods

Cited by in corpus (1)

• Adaptive Multi-view Rule Discovery for Weakly-Supervised Compatible Products Prediction