Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilation (2303.06516v3)

Abstract: The use of Shap scores has become widespread in Explainable AI. However, their computation is in general intractable, in particular when done with a black-box classifier, such as neural network. Recent research has unveiled classes of open-box Boolean Circuit classifiers for which Shap can be computed efficiently. We show how to transform binary neural networks into those circuits for efficient Shap computation.We use logic-based knowledge compilation techniques. The performance gain is huge, as we show in the light of our experiments.