Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV) methods provide a principled framework for feature attribution in complex models but incur high computational costs, limiting their scalability in high-dimensional settings. We propose Stochastic Iterative Momentum for Shapley Value Approximation (SIM-Shapley), a stable and efficient SV approximation method inspired by stochastic optimization. We analyze variance theoretically, prove linear $Q$-convergence, and demonstrate improved empirical stability and low bias in practice on real-world datasets. In our numerical experiments, SIM-Shapley reduces computation time by up to 85% relative to state-of-the-art baselines while maintaining comparable feature attribution quality. Beyond feature attribution, our stochastic mini-batch iterative framework extends naturally to a broader class of sample average approximation problems, offering a new avenue for improving computational efficiency with stability guarantees. Code is publicly available at https://github.com/nliulab/SIM-Shapley.

翻译：可解释人工智能（XAI）对于可信机器学习（ML）至关重要，尤其是在医疗和金融等高风险领域。Shapley值（SV）方法为复杂模型中的特征归因提供了理论框架，但其计算成本高昂，限制了在高维场景下的可扩展性。我们提出了一种受随机优化启发的稳定高效SV近似方法——基于随机迭代动量的Shapley值近似（SIM-Shapley）。我们从理论上分析了方差，证明了其线性$Q$收敛性，并在真实数据集上验证了该方法具有更优的经验稳定性与低偏差特性。数值实验表明，相较于最先进的基线方法，SIM-Shapley在保持相当特征归因质量的同时，计算时间最高可减少85%。除特征归因外，我们的随机小批量迭代框架可自然扩展至更广泛的样本平均近似问题类别，为在稳定性保证下提升计算效率提供了新途径。代码公开于 https://github.com/nliulab/SIM-Shapley。