Skip to yearly menu bar Skip to main content


HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation

Lu Chen · Siyu Lou · Keyan Zhang · JIN HUANG · Quanshi Zhang

Exhibit Hall 1 #634
[ ]
[ PDF [ Poster


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.

Chat is not available.