RKHS-SHAP: Shapley Values for Kernel Methods. (arXiv:2110.09167v2 [stat.ML] UPDATED)

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 …

arxiv kernel ml shap values