Sensitivity Verification for Decision Tree Ensembles
Keywords: Robustness verification, Sensitivity analysis, SAT solvers, efficient encodings, NP-hardness, fairness
Abstract: Tree ensemble models, such as Gradient Boosted Decision Trees (GBDTs) and
random forests, are widely popular models for a variety of machine learning tasks.
The power of these models comes from the ensemble of decision trees, which
makes analysis of such models significantly harder than for single trees. As a
result, recent work has focused on developing exact and approximate techniques
for questions such as robustness verification, fairness and explainability, for such
models of tree ensembles.
In this paper, we focus on a specific problem of feature sensitivity for additive
decision tree ensembles and build a formal verification framework for it. We start
by showing theoretical (NP-)hardness of the problem and explain how it relates
to other verification problems. Next, we provide a novel encoding of the problem
using pseudo-Boolean constraints. Based on this encoding, we develop a tunable
algorithm to perform sensitivity analysis, which can trade off precision for running
time. We implement our algorithm and study its performance on a suite of GBDT
benchmarks from the literature. Our experiments show the practical utility of our
approach and its improved performance compared to existing approaches.
Primary Area: alignment, fairness, safety, privacy, and societal considerations
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 14006
Loading