From unbiased MDI Feature Importance to Explainable AI for Trees

2020/03/26 by Markus Loecher, Loecher, Markus · 1 citation
Computer Science · Mathematics · #Computation (stat.CO) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #cs.LG #stat.CO #stat.ML

paper · pdf · doi:10.48550/arxiv.2003.12043

arXiv admin note: text overlap with arXiv:2003.02106

arxiv created 2021/09/30 · arxiv updated 2021/10/01

Abstract

We attempt to give a unifying view of the various recent attempts to (i) improve the interpretability of tree-based models and (ii) debias the the default variable-importance measure in random Forests, Gini importance. In particular, we demonstrate a common thread among the out-of-bag based bias correction methods and their connection to local explanation for trees. In addition, we point out a bias caused by the inclusion of inbag data in the newly developed explainable AI for trees algorithms.

Citations

• Unbiased variable importance for random forests

Cited by

• Data-driven advice for interpreting local and global model predictions in bioinformatics problems

Related

• A Debiased MDI Feature Importance Measure for Random Forests
• Interpreting Deep Forest through Feature Contribution and MDI Feature Importance
• Trees, forests, and impurity-based variable importance
• Unbiased Measurement of Feature Importance in Tree-Based Methods
• Local MDI+: Local Feature Importances for Tree-Based Models