基于树模型的区间值SHAP

中文摘要 AI 辅助

Shapley值是最受欢迎的特征归因解释方法之一，目前已开发出针对表格数据的最优树模型计算或估计Shapley值的高效方法。但已知Shapley值对微小且现实的变化可能具有高度不鲁棒性。本文提出一种基于不精确狄利克雷模型（IDM）的方法，用于分析决策树和随机森林中Shapley值的鲁棒性。技术上，通过向树的叶节点随机引入少量未标注实例，量化并分析区间值Shapley值，该值可遵循处理不完整数据的通用原则（悲观原则与平均原则）定义。本文推导了多种理论结果，可实现区间值Shapley值的高效计算，还表明所提方法可直接推广到Banzhaf值的情况。最后通过多个案例研究和实验，说明区间值Shapley值的特性及其在消除无信息特征偏差中的应用。

英文摘要

Shapley values are among the most popular feature-attribution explanations. Efficient approaches for computing/estimating Shapley values for tree-based models, which are state-of-the-art for tabular data sets, have been developed. However, it is known that Shapley values can be (highly) unrobust due to small and realistic changes. In this paper, we propose an imprecise Dirichlet model (IDM) based method to analyze the robustness of Shapley values in decision trees and random forests. Technically, it is done by quantifying and analyzing the interval-valued Shapley values when a few unannotated instances are randomly introduced to the leaves of the trees. The interval-valued Shapley values can be defined following common principles in handling incomplete data: the pessimistic and averaging principles. We derive various theoretical results that lead to efficient computation of the interval-valued Shapley values. We also show that the proposed method can be straightforwardly generalized to the case of Banzhaf values. We then present various case studies and experiments to illustrate the behaviour of the proposed interval-valued Shapley values and their applications in debiasing uninformative features.

发表机构

• Université de technologie de Compiègne（贡比涅技术大学）
• IUT de l’Oise, Université de Picardie Jules Verne（皮卡迪大学儒勒·凡尔纳校区瓦兹省大学技术学院）

机构由 AI 辅助整理，请以论文原文为准。