RKHS-SHAP: Shapley Values for Kernel Methods
This work addresses the need for consistent and individualized feature attribution in kernel methods, which is incremental as it adapts existing Shapley value frameworks to a new domain.
The authors tackled the problem of feature attribution for kernel methods by proposing RKHS-SHAP, a method that efficiently computes Shapley values for kernel machines, showing theoretical robustness to local perturbations and enabling robust and fair learning through a Shapley regularizer.
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.