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, 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：针对个体归因分数在Shapley值（SV）中的局限性，可解释人工智能（XAI）领域近期深入研究了特征或数据点之间的复杂交互作用。特别地，Shapley交互作用指数（SII）等SV扩展方法被提出，以在保留SV公理化基础的前提下继续发挥作用。然而，与SV类似，精确计算这些指数在计算上仍然难以实现。为此，我们提出SVARM-IQ——一种基于采样的方法，能够高效近似任意阶基于Shapley的交互作用指数。通过利用新颖的分层表示，SVARM-IQ可适用于包括SII在内的广泛交互作用指数。我们给出了其近似质量的非渐近理论保证，并通过实验证明，在实用XAI场景中，SVARM-IQ在不同模型类别和应用领域均达到了最先进的估计效果。