Abstract
Shapley value-based feature attribution methods face challenges in scenarios involving complex feature interactions and causal relationships, even when a causal structure is provided. Existing methods typically adopt a node-centric view, attributing importance solely to individual features. Consequently, they often fail to simultaneously capture the externality and exogenous influence of features, leading to unreasonable interpretations.
To overcome these limitations, we propose a novel feature attribution method called DAG-SHAP, which is based on edge intervention. DAG-SHAP treats each feature edge as an individual attribution object, ensuring that both externality and exogenous contributions of features are appropriately captured. Additionally, we introduce an approximation method for efficiently computing DAG-SHAP.
Extensive experiments on both real and synthetic datasets validate the effectiveness of DAG-SHAP. Our code is available at GitHub.
Blogger's Review: The DAG-SHAP method effectively addresses the shortcomings of existing feature attribution approaches, especially in scenarios with complex feature interactions, showcasing significant application potential. Its comprehensive capture of externality and exogenous influences provides a more reasonable interpretative framework for data analysis. Looking forward to seeing more practical applications based on this method.