HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Chen, Lu, Siyu Lou, Zhang, Keyan, Huang, Jin, Zhang, Quanshi
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 01.12.2023
Subjects
Artificial neural networks
Computer architecture
Propagation
Online AccessGet full text

Cover

More Information
Summary:The Shapley value is widely regarded as a trustworthy attribution metric. However, when people use Shapley values to explain the attribution of input variables of a deep neural network (DNN), it usually requires a very high computational cost to approximate relatively accurate Shapley values in real-world applications. Therefore, we propose a novel network architecture, the HarsanyiNet, which makes inferences on the input sample and simultaneously computes the exact Shapley values of the input variables in a single forward propagation. The HarsanyiNet is designed on the theoretical foundation that the Shapley value can be reformulated as the redistribution of Harsanyi interactions encoded by the network.
ISSN:2331-8422