HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation
This addresses the problem of inefficient Shapley value computation for practitioners in explainable AI, offering a direct and fast solution.
The paper tackles the high computational cost of approximating accurate Shapley values for explaining deep neural networks by proposing HarsanyiNet, a novel architecture that computes exact Shapley values in a single forward propagation, eliminating the need for expensive approximations.
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.