Title | ||
---|---|---|
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. |
Year | Venue | DocType |
---|---|---|
2019 | CoRR | Journal |
Volume | Citations | PageRank |
abs/1906.01297 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xavier Renard | 1 | 9 | 2.54 |
Nicolas Woloszko | 2 | 0 | 0.34 |
Jonathan Aigrain | 3 | 19 | 2.16 |
Marcin Detyniecki | 4 | 330 | 39.95 |