On Importance Sampling and Multilinear Extensions for Approximating Shapley Values with Applications to Explainable Artificial Intelligence (opens in new tab)

Tim Pollmann and Jochen Staudacher Complexities 2026, 2(1), 7 Shapley values are the most widely used point-valued solution concept for cooperative games and have recently garnered attention for their applicability in explainable machine learning. Due to the complexity of Shapley value computation, users mostly resort to Monte Carlo approximations for large problems. We take a detailed look at an approximation method grounded in multilinear extensions proposed in 2021 under the name “Owen sam...