Versatile Verification of Tree Ensembles
This work addresses the need for versatile verification in machine learning to ensure model compliance with requirements, representing a novel method for a known bottleneck rather than a foundational advancement.
The paper tackles the problem of verifying whether tree ensemble models like random forests and gradient boosting decision trees satisfy certain properties such as fairness or legal requirements, by introducing a generic algorithm called Veritas that outperforms previous state-of-the-art methods by generating exact solutions more frequently, producing tighter bounds, and offering orders of magnitude speed-ups.
Machine learned models often must abide by certain requirements (e.g., fairness or legal). This has spurred interested in developing approaches that can provably verify whether a model satisfies certain properties. This paper introduces a generic algorithm called Veritas that enables tackling multiple different verification tasks for tree ensemble models like random forests (RFs) and gradient boosting decision trees (GBDTs). This generality contrasts with previous work, which has focused exclusively on either adversarial example generation or robustness checking. Veritas formulates the verification task as a generic optimization problem and introduces a novel search space representation. Veritas offers two key advantages. First, it provides anytime lower and upper bounds when the optimization problem cannot be solved exactly. In contrast, many existing methods have focused on exact solutions and are thus limited by the verification problem being NP-complete. Second, Veritas produces full (bounded suboptimal) solutions that can be used to generate concrete examples. We experimentally show that Veritas outperforms the previous state of the art by (a) generating exact solutions more frequently, (b) producing tighter bounds when (a) is not possible, and (c) offering orders of magnitude speed ups. Subsequently, Veritas enables tackling more and larger real-world verification scenarios.