Accelerating Shapley Explanation via Contributive Cooperator Selection
This addresses the computational bottleneck for Shapley-based explanations in real-world applications with limited resources, representing an incremental improvement over existing methods.
The paper tackles the problem of exponentially growing complexity in computing Shapley values for DNN model explanations by proposing SHEAR, a method that accelerates computation by selecting only a few feature coalitions, resulting in consistent outperformance of state-of-the-art baselines across metrics like absolute error and running speed.
Even though Shapley value provides an effective explanation for a DNN model prediction, the computation relies on the enumeration of all possible input feature coalitions, which leads to the exponentially growing complexity. To address this problem, we propose a novel method SHEAR to significantly accelerate the Shapley explanation for DNN models, where only a few coalitions of input features are involved in the computation. The selection of the feature coalitions follows our proposed Shapley chain rule to minimize the absolute error from the ground-truth Shapley values, such that the computation can be both efficient and accurate. To demonstrate the effectiveness, we comprehensively evaluate SHEAR across multiple metrics including the absolute error from the ground-truth Shapley value, the faithfulness of the explanations, and running speed. The experimental results indicate SHEAR consistently outperforms state-of-the-art baseline methods across different evaluation metrics, which demonstrates its potentials in real-world applications where the computational resource is limited.