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.

presented at 2019 ICML Workshop on Human in the Loop Learning (HILL 2019), Long Beach, USA

References in corpus (3)

• Correlation and variable importance in random forests
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
• Correlated variables in regression: clustering and sparse estimation

Cited by in corpus (1)

• Trepan Reloaded: A Knowledge-driven Approach to Explaining Artificial Neural Networks