HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

作     者：Chen, Lu Lou, Siyu Zhang, Keyan Huang, Jin Zhang, Quanshi 

作者机构：Shanghai Jiao Tong University China Eastern Institute for Advanced Study China The Department of Computer Science and Engineering The John Hopcroft Center The Shanghai Jiao Tong University China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Network architecture 

摘      要：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. Copyright © 2023, The Authors. All rights reserved.