Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

Among explainability techniques, SHAP stands out as one of the most popular, but often overlooks the causal structure of the problem. In response, do-SHAP employs interventional queries, but its reliance on estimands hinders its practical application. To address this problem, we propose the use of estimand-agnostic approaches, which allow for the estimation of any identifiable query from a single model, making do-SHAP feasible on complex graphs. We also develop a novel algorithm to significantly accelerate its computation at a negligible cost, as well as a method to explain inaccessible Data Generating Processes. We demonstrate the estimation and computational performance of our approach, and validate it on two real-world datasets, highlighting its potential in obtaining reliable explanations. Several works [8, 9, 10, 11] discussed the limitations of non-causal SHAP and proposed limited approaches with a causal interpretation. Jung et al. [12] proposed do-SHAP, defining ν as a causal, 39th Conference on Neural Information Processing Systems (NeurIPS 2025).