GPUTreeShap: massively parallel exact calculation of SHAP scores for tree ensembles

SHapley Additive exPlanation (SHAP) values (Lundberg & Lee, 2017) provide a game theoretic interpretation of the predictions of machine learning models based on Shapley values (Shapley, 1953). While exact calculation of SHAP values is computationally intractable in general, a recursive polynomia...

Full description

Saved in:

Bibliographic Details
Published in:	PeerJ. Computer science Vol. 8; p. e880
Main Authors:	Mitchell, Rory, Frank, Eibe, Holmes, Geoffrey
Format:	Journal Article
Language:	English
Published:	United States PeerJ. Ltd 05.04.2022 PeerJ, Inc PeerJ Inc
Subjects:	Algorithms Algorithms and Analysis of Algorithms Central processing units CPUs Data Mining and Machine Learning Decision trees Distributed and Parallel Computing GPU computing Graphics processing units Hardware Interpretability Machine learning Mathematical analysis Multiprocessing Operations research Parallel processing Pipelining (computers) Polynomials Random variables Semiconductor industry Shapley values United States Shapley values Interpretability GPU computing
ISSN:	2376-5992, 2376-5992
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!