Feature attribution for kernel methods is often heuristic and not individualised for each prediction. To address this, we turn to the concept of Shapley values~(SV), a coalition game theoretical framework that has previously been applied to different machine learning model interpretation tasks, such as linear models, tree ensembles and deep networks. By analysing SVs from a functional perspective, we propose \textsc{RKHS-SHAP}, an attribution method for kernel machines that can efficiently compute both \emph{Interventional} and \emph{Observational Shapley values} using kernel mean embeddings of distributions. We show theoretically that our method is robust with respect to local perturbations - a key yet often overlooked desideratum for consistent model interpretation. Further, we propose \emph{Shapley regulariser}, applicable to a general empirical risk minimisation framework, allowing learning while controlling the level of specific feature's contributions to the model. We demonstrate that the Shapley regulariser enables learning which is robust to covariate shift of a given feature and fair learning which controls the SVs of sensitive features.
翻译:内核方法的特性属性通常是杂乱的, 而不是针对每种预测的个性化。 为了解决这个问题, 我们转而研究Shapley value ~ (SV) 的概念, 这是一种联合游戏理论框架, 过去曾应用于不同的机器学习模型解释任务, 如线性模型、 树群和深网络。 通过从功能角度分析 SVs, 我们建议 \ textsc{ RKHS- SHAP} 内核机器的特性属性方法, 它可以有效地计算 emph{ Interventional} 和 emph{ 观察性沙皮利值, 使用分布的内核平均值嵌。 我们从理论上表明, 我们的方法在本地扰动模型解释方面是稳健的, 一种关键但经常被忽视的边际解释 。 此外, 我们建议 \ emph{ Shaple maniser, 适用于一般的经验风险最小化框架, 允许在控制特定特性对模型的贡献水平的同时学习 。 我们证明 Shaple 正规化 能够学习对特定特性的敏感性特性特性进行稳健和公平学习, 。