论文标题
加权图：分析和改善基于沙普利的特征属性
WeightedSHAP: analyzing and improving Shapley based feature attributions
论文作者
论文摘要
沙普利价值是衡量单个特征影响的流行方法。虽然Shapley功能归因是基于游戏理论的Desiderata，但在某些机器学习设置中，其某些约束可能不太自然，从而导致不直觉的模型解释。特别是，Shapley值对所有边际贡献都使用相同的权重 - 即，当给出大量其他功能时，当给出少数其他功能时，它具有相同的重要性。如果较大的功能集比较小的功能集更具信息性，则此属性可能是有问题的。我们的工作对沙普利特征归因的潜在局限性进行了严格的分析。我们通过为较小的影响力特征分配更大的属性来确定Shapley值在数学上次优的设置。在这一观察结果的推动下，我们提出了加权图，它概括了沙普利价值，并了解了直接从数据中关注的边缘贡献。在几个现实世界数据集上，我们证明了加权图所标识的有影响力的功能可以更好地概括模型的预测，而不是沙普利值确定的特征。
Shapley value is a popular approach for measuring the influence of individual features. While Shapley feature attribution is built upon desiderata from game theory, some of its constraints may be less natural in certain machine learning settings, leading to unintuitive model interpretation. In particular, the Shapley value uses the same weight for all marginal contributions -- i.e. it gives the same importance when a large number of other features are given versus when a small number of other features are given. This property can be problematic if larger feature sets are more or less informative than smaller feature sets. Our work performs a rigorous analysis of the potential limitations of Shapley feature attribution. We identify simple settings where the Shapley value is mathematically suboptimal by assigning larger attributions for less influential features. Motivated by this observation, we propose WeightedSHAP, which generalizes the Shapley value and learns which marginal contributions to focus directly from data. On several real-world datasets, we demonstrate that the influential features identified by WeightedSHAP are better able to recapitulate the model's predictions compared to the features identified by the Shapley value.
