English

Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees

Machine Learning 2019-06-05 v1 Machine Learning

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.

Keywords

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

R2 v1 2026-06-23T09:40:45.265Z