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.

提出了一种新方法 SHEAR 来显著加速 DNN 模型的 Shapley 解释，其选择的输入特征 coalitions 遵循了 Shapley 链规则来最小化绝对误差，从而使计算既高效又准确。实验结果表明，SHEAR 在绝对误差、解释的忠诚度和运行速度等多个指标上始终优于现有基线方法，展示了其在计算资源有限的真实应用中的潜力。