Concept Tree: High-Level Representation of Variables for More Interpretable Surrogate Decision Trees
This addresses the challenge of making black-box models more comprehensible for users in domains like economics, though it is incremental as it builds on existing surrogate methods.
The paper tackles the problem of generating interpretable surrogate explanations for black-box classifiers on high-dimensional tabular data with correlated variables, resulting in improved human-interpretability while maintaining accuracy and fidelity on a macroeconomic dataset with 134 variables.
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.