Learning Model Agnostic Explanations via Constraint Programming

TL;DR

This paper introduces a constraint programming approach to generate model-agnostic explanations for black box classifiers, providing theoretical guarantees and outperforming existing heuristics in empirical tests.

Contribution

It formulates the explanation task as a constraint optimization problem with PAC-style guarantees, advancing interpretability methods for complex models.

Findings

Outperforms the Anchors heuristic in empirical evaluations

Provides PAC-style theoretical guarantees for explanations

Effective across various datasets

Abstract

Interpretable Machine Learning faces a recurring challenge of explaining the predictions made by opaque classifiers such as ensemble models, kernel methods, or neural networks in terms that are understandable to humans. When the model is viewed as a black box, the objective is to identify a small set of features that jointly determine the black box response with minimal error. However, finding such model-agnostic explanations is computationally demanding, as the problem is intractable even for binary classifiers. In this paper, the task is framed as a Constraint Optimization Problem, where the constraint solver seeks an explanation of minimum error and bounded size for an input data instance and a set of samples generated by the black box. From a theoretical perspective, this constraint programming approach offers PAC-style guarantees for the output explanation. We evaluate the approach empirically on various datasets and show that it statistically outperforms the state-of-the-art heuristic Anchors method.