Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation
It addresses the need for interpretable surrogate models in model distillation, but it is incremental as it compares existing methods without introducing new ones.
This paper tackled the problem of interpreting black box machine learning models by using model-based trees as surrogate models, comparing four algorithms (SLIM, GUIDE, MOB, CTree) and providing user-specific recommendations based on fidelity, interpretability, stability, and interaction capture.
Surrogate models play a crucial role in retrospectively interpreting complex and powerful black box machine learning models via model distillation. This paper focuses on using model-based trees as surrogate models which partition the feature space into interpretable regions via decision rules. Within each region, interpretable models based on additive main effects are used to approximate the behavior of the black box model, striking for an optimal balance between interpretability and performance. Four model-based tree algorithms, namely SLIM, GUIDE, MOB, and CTree, are compared regarding their ability to generate such surrogate models. We investigate fidelity, interpretability, stability, and the algorithms' capability to capture interaction effects through appropriate splits. Based on our comprehensive analyses, we finally provide an overview of user-specific recommendations.