Feature interactions drive much of the predictive power of machine learning models, yet existing explanation methods only detect and quantify interactions without revealing their functional form, or visualize only restricted interaction types. We propose Surrogate-based Analysis of Interactions via Local effect Smooths (SAILS), a model-agnostic framework that analyzes pairwise interactions through interpretable generalized additive model (GAM) surrogates fitted to the local effects of a black-box model. For each interval of a feature of interest, the surrogate smooth terms isolate the interaction components on derivative level, enabling (i) interaction detection through a heuristic derived from significance tests on smooth terms, (ii) interaction form categorization into linear, product-separable, and non-product-separable types, and (iii) tailored, interpretable visualizations for each interaction type. We empirically validate the framework through controlled simulations and a real-world task, demonstrating its effectiveness for pairwise interactions, with limitations under strong feature correlations and higher-order interactions. SAILS fills a notable gap in the XAI toolbox, going beyond detection of interactions alone to characterizing their functional form.

翻译：特征交互是机器学习模型预测能力的重要驱动力，但现有解释方法仅能检测和量化交互作用，无法揭示其函数形式，或仅能可视化受限的交互类型。我们提出基于局部效应平滑的替代模型交互分析（SAILS）框架，该框架通过可解释的广义加性模型（GAM）替代模型，拟合黑箱模型的局部效应来分析成对交互。对于感兴趣特征的每个区间，替代模型的平滑项在导数层面分离交互成分，从而实现：（i）基于平滑项显著性检验启发式方法的交互检测；（ii）将交互形式分类为线性、乘积可分离和非乘积可分离类型；以及（iii）为每种交互类型提供定制化的可解释可视化。通过受控模拟和真实世界任务的经验验证，我们证明了该框架在成对交互分析中的有效性，但其在强特征相关性和高阶交互场景下存在局限性。SAILS填补了XAI工具箱中交互检测与功能形式表征之间的显著空白，超越了单纯的交互检测，实现了交互功能形式的刻画。