Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Borui, Tian, Baotong, Zheng, Wenzhao, Zhou, Jie, Lu, Jiwen
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2311.01010
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917672930770944
author Zhang, Borui
Tian, Baotong
Zheng, Wenzhao
Zhou, Jie
Lu, Jiwen
author_facet Zhang, Borui
Tian, Baotong
Zheng, Wenzhao
Zhou, Jie
Lu, Jiwen
contents Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity as the number of features increases. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. In our analysis of existing approaches, we observe that stochastic estimators can be unified as a linear transformation of randomly summed values from feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
format Preprint
id arxiv_https___arxiv_org_abs_2311_01010
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fast Shapley Value Estimation: A Unified Approach
Zhang, Borui
Tian, Baotong
Zheng, Wenzhao
Zhou, Jie
Lu, Jiwen
Machine Learning
Computer Vision and Pattern Recognition
Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity as the number of features increases. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. In our analysis of existing approaches, we observe that stochastic estimators can be unified as a linear transformation of randomly summed values from feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
title Fast Shapley Value Estimation: A Unified Approach
topic Machine Learning
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2311.01010