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.

翻译：Shap分数在可解释人工智能中的应用已十分广泛。然而，其计算通常具有难解性，尤其是针对神经网络这类黑箱分类器时。最新研究揭示了若干开放箱布尔电路分类器类别，这些类别可实现Shap的高效计算。本文展示了如何将二值神经网络转化为此类电路，以支持高效的Shap计算。我们采用了基于逻辑的知识编译技术。实验结果表明，该方法能带来显著的计算性能提升。