Learning Model Agnostic Explanations via Constraint Programming
This addresses the challenge of interpretability in machine learning for users needing human-understandable explanations, though it is incremental as it builds on existing model-agnostic approaches.
The paper tackles the problem of explaining predictions from opaque classifiers by framing it as a constraint optimization problem to find minimal-error, bounded-size explanations, and empirically shows it outperforms the state-of-the-art Anchors method.
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.