Fast Shapley Value Estimation: A Unified Approach
This work addresses a computational bottleneck for researchers and practitioners using Shapley values in explainable AI, representing an incremental improvement over existing methods.
The paper tackled the exponential complexity of computing Shapley values for black-box models by proposing SimSHAP, a simple amortized estimator that significantly accelerates computation while maintaining accuracy, as validated on tabular and image datasets.
Shapley values have emerged as a widely accepted and trustworthy tool, grounded in theoretical axioms, for addressing challenges posed by black-box models like deep neural networks. However, computing Shapley values encounters exponential complexity as the number of features increases. Various approaches, including ApproSemivalue, KernelSHAP, and FastSHAP, have been explored to expedite the computation. In our analysis of existing approaches, we observe that stochastic estimators can be unified as a linear transformation of randomly summed values from feature subsets. Based on this, we investigate the possibility of designing simple amortized estimators and propose a straightforward and efficient one, SimSHAP, by eliminating redundant techniques. Extensive experiments conducted on tabular and image datasets validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.