Addressing the limitations of individual attribution scores via the Shapley value (SV), the field of explainable AI (XAI) has recently explored intricate interactions of features or data points. In particular, \mbox{extensions}~of~the SV, such as the Shapley Interaction Index (SII), have been proposed as a measure to still benefit from the axiomatic basis of the SV. However, similar to the SV, their exact computation remains computationally prohibitive. Hence, we propose with SVARM-IQ a sampling-based approach to efficiently approximate Shapley-based interaction indices of any order. SVARM-IQ can be applied to a broad class of interaction indices, including the SII, by leveraging a novel stratified representation. We provide non-asymptotic theoretical guarantees on its approximation quality and empirically demonstrate that SVARM-IQ achieves state-of-the-art estimation results in practical XAI scenarios on different model classes and application domains.

翻译：为应对基于夏普利值（SV）的个体归因分数局限性，可解释人工智能（XAI）领域近期深入研究了特征或数据点间的复杂交互作用。具体而言，作为SV的扩展方法（如夏普利交互指数SII），已被提出以继承SV公理基础的益处。然而，与SV类似，其精确计算仍存在计算不可行性。为此，我们提出SVARM-IQ——一种基于采样的方法，可高效逼近任意阶的夏普利交互指数。SVARM-IQ通过创新性分层表征，适用于包括SII在内的广泛交互指数类别。我们提供了逼近质量的非渐近理论保证，并通过实验证明，在不同模型类别与应用场景的实际XAI任务中，SVARM-IQ达到了当前最先进的估计性能。