Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees
Abstract
Interpretable surrogates of black-box predictors trained on high-dimensional tabular datasets can struggle to generate comprehensible explanations in the presence of correlated variables. We propose a model-agnostic interpretable surrogate that provides global and local explanations of black-box classifiers to address this issue. We introduce the idea of concepts as intuitive groupings of variables that are either defined by a domain expert or automatically discovered using correlation coefficients. Concepts are embedded in a surrogate decision tree to enhance its comprehensibility. First experiments on FRED-MD, a macroeconomic database with 134 variables, show improvement in human-interpretability while accuracy and fidelity of the surrogate model are preserved.
Cite
@article{arxiv.1906.01297,
title = {Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees},
author = {Xavier Renard and Nicolas Woloszko and Jonathan Aigrain and Marcin Detyniecki},
journal= {arXiv preprint arXiv:1906.01297},
year = {2019}
}
Comments
presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA