论文标题
理解介入的三齿：如何以及为什么运作
Understanding Interventional TreeSHAP : How and Why it Works
论文作者
论文摘要
Shapley值在可解释的机器学习中无处不在，因为它们在Shap库中的强大理论背景和有效的实现。计算这些值以前就不透明模型的输入特征数量引起了指数成本。现在，通过有效的实施，例如介入的三级，这一指数负担可以减轻，假设人们正在解释决策树的集合。尽管介入的三齿轮越来越流行，但它仍然缺乏正式的证据，证明其工作方式/原因。我们提供了这样的证据，目的不仅是提高算法的透明度，而且还鼓励进一步发展这些思想。值得注意的是，我们的介入式三室的证明很容易适应Shapley-Taylor指数和一hot编码的功能。
Shapley values are ubiquitous in interpretable Machine Learning due to their strong theoretical background and efficient implementation in the SHAP library. Computing these values previously induced an exponential cost with respect to the number of input features of an opaque model. Now, with efficient implementations such as Interventional TreeSHAP, this exponential burden is alleviated assuming one is explaining ensembles of decision trees. Although Interventional TreeSHAP has risen in popularity, it still lacks a formal proof of how/why it works. We provide such proof with the aim of not only increasing the transparency of the algorithm but also to encourage further development of these ideas. Notably, our proof for Interventional TreeSHAP is easily adapted to Shapley-Taylor indices and one-hot-encoded features.
