Exactly Computing do-Shapley Values
Abstract
Structural Causal Models (SCM) are a powerful framework for describing complicated dynamics across the natural sciences. A particularly elegant way of interpreting SCMs is do-Shapley, a game-theoretic method of quantifying the average effect of variables across exponentially many interventions. Like Shapley values, computing do-Shapley values generally requires evaluating exponentially many terms. The foundation of our work is a reformulation of do-Shapley values in terms of the irreducible sets of the underlying SCM. Leveraging this insight, we can exactly compute do-Shapley values in time linear in the number of irreducible sets , which itself can range from to depending on the graph structure of the SCM. Since is unknown a priori, we complement the exact algorithm with an estimator that, like general Shapley value estimators, can be run with any query budget. As the query budget approaches , our estimators can produce more accurate estimates than prior methods by several orders of magnitude, and, when the budget reaches , return the Shapley values up to machine precision. Beyond computational speed, we also reduce the identification burden: we prove that non-parametric identifiability of do-Shapley values requires only the identification of interventional effects for the singleton coalitions, rather than all classes.
Keywords
Cite
@article{arxiv.2602.07203,
title = {Exactly Computing do-Shapley Values},
author = {R. Teal Witter and Álvaro Parafita and Tomas Garriga and Maximilian Muschalik and Fabian Fumagalli and Axel Brando and Lucas Rosenblatt},
journal= {arXiv preprint arXiv:2602.07203},
year = {2026}
}