论文标题
了解具有添加重要性度量的全球功能贡献
Understanding Global Feature Contributions With Additive Importance Measures
论文作者
论文摘要
了解复杂的机器学习模型的内部工作是一个长期存在的问题，最新的研究集中在局部解释性上。为了评估全球意义上各个输入特征的作用，我们探讨了通过与每个功能相关的预测能力来定义特征重要性的观点。我们介绍了两个预测能力（基于模型和通用）的概念，并通过添加重要性度量的框架将这种方法形式化，该方法统一了文献中的许多方法。然后，我们提出了Sage，一种模型 - 不足的方法，可以在考虑特征相互作用的同时量化预测能力。我们的实验表明，可以有效地计算出SAGE，并且比其他方法更准确地分配了重要性值。
Understanding the inner workings of complex machine learning models is a long-standing problem and most recent research has focused on local interpretability. To assess the role of individual input features in a global sense, we explore the perspective of defining feature importance through the predictive power associated with each feature. We introduce two notions of predictive power (model-based and universal) and formalize this approach with a framework of additive importance measures, which unifies numerous methods in the literature. We then propose SAGE, a model-agnostic method that quantifies predictive power while accounting for feature interactions. Our experiments show that SAGE can be calculated efficiently and that it assigns more accurate importance values than other methods.
