all AI news
RKHS-SHAP: Shapley Values for Kernel Methods. (arXiv:2110.09167v2 [stat.ML] UPDATED)
May 27, 2022, 1:11 a.m. | Siu Lun Chau, Robert Hu, Javier Gonzalez, Dino Sejdinovic
stat.ML updates on arXiv.org arxiv.org
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 …
More from arxiv.org / stat.ML updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Alternant Data Engineering
@ Aspire Software | Angers, FR
Senior Software Engineer, Generative AI
@ Google | Dublin, Ireland