Data-Aware and Scalable Sensitivity Analysis for Decision Tree Ensembles

TL;DR

This paper introduces a data-aware, scalable sensitivity analysis framework for decision tree ensembles, improving interpretability and robustness verification by generating realistic, close-to-data examples using advanced optimization techniques.

Contribution

It presents novel MILP and SMT-based methods for efficient, data-aware sensitivity verification, including handling multiclass ensembles and large models, with extensive experimental validation.

Findings

Scalability to ensembles with up to 800 trees of depth 8.

Significant speed-ups over existing methods.

Enhanced interpretability through realistic sensitivity examples.

Abstract

Decision tree ensembles are widely used in critical domains, making robustness and sensitivity analysis essential to their trustworthiness. We study the feature sensitivity problem, which asks whether an ensemble is sensitive to a specified subset of features -- such as protected attributes -- whose manipulation can alter model predictions. Existing approaches often yield examples of sensitivity that lie far from the training distribution, limiting their interpretability and practical value. We propose a data-aware sensitivity framework that constrains the sensitive examples to remain close to the dataset, thereby producing realistic and interpretable evidence of model weaknesses. To this end, we develop novel techniques for data-aware search using a combination of mixed-integer linear programming (MILP) and satisfiability modulo theories (SMT) encodings. Our contributions are fourfold. First, we strengthen the NP-hardness result for sensitivity verification, showing it holds even for trees of depth 1. Second, we develop MILP-optimizations that significantly speed up sensitivity verification for single ensembles and for the first time can also handle multiclass tree ensembles. Third, we introduce a data-aware framework generating realistic examples close to the training distribution. Finally, we conduct an extensive experimental evaluation on large tree ensembles, demonstrating scalability to ensembles with up to 800 trees of depth 8, achieving substantial improvements over the state of the art. This framework provides a practical foundation for analyzing the reliability and fairness of tree-based models in high-stakes applications.