Guardado en:
Detalles Bibliográficos
Autores principales: Gorji, Ali, Amrollahi, Andisheh, Krause, Andreas
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2410.06300
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909864292253696
author Gorji, Ali
Amrollahi, Andisheh
Krause, Andreas
author_facet Gorji, Ali
Amrollahi, Andisheh
Krause, Andreas
contents SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm for computing SHAP values in both black-box setting and tree-based models. Motivated by spectral bias in real-world predictors, we first approximate models using compact Fourier representations, exactly for trees and approximately for black-box models. In the second stage, we introduce a closed-form formula for {\em exactly} computing SHAP values using the Fourier representation, that ``linearizes'' the computation into a simple summation and is amenable to parallelization. As the Fourier approximation is computed only once, our method enables amortized SHAP value computation, achieving significant speedups over existing methods and a tunable trade-off between efficiency and precision.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06300
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SHAP values via sparse Fourier representation
Gorji, Ali
Amrollahi, Andisheh
Krause, Andreas
Machine Learning
SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm for computing SHAP values in both black-box setting and tree-based models. Motivated by spectral bias in real-world predictors, we first approximate models using compact Fourier representations, exactly for trees and approximately for black-box models. In the second stage, we introduce a closed-form formula for {\em exactly} computing SHAP values using the Fourier representation, that ``linearizes'' the computation into a simple summation and is amenable to parallelization. As the Fourier approximation is computed only once, our method enables amortized SHAP value computation, achieving significant speedups over existing methods and a tunable trade-off between efficiency and precision.
title SHAP values via sparse Fourier representation
topic Machine Learning
url https://arxiv.org/abs/2410.06300