Efficient Computation of Shap Explanation Scores for Neural Network Classifiers via Knowledge Compilation

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.