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 in:arXiv.org 2023-12
Main Authors: Chen, Lu, Siyu Lou, Zhang, Keyan, Huang, Jin, Zhang, Quanshi
Format: Article
Language:English
Subjects:
Artificial neural networks
Computer architecture
Propagation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
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