IMEX: Interaction-Based Model Explanation

Computer Science > Artificial Intelligence arXiv:2607.14096 (cs) [Submitted on 16 Apr 2026] Title: IMEX Interaction-Based Model Explanation Authors: Emiliano Massi

计算机科学 > 人工智能 arXiv:2607.14096 (cs) [提交于 2026 年 4 月 16 日] 标题：IMEX：基于交互的模型解释 作者：Emiliano Massi

---

Abstract: In predictive modeling, the ability to explain why a model produces a given target prediction has become increasingly important [5, 10]. Black-box models do not provide a transparent description of the internal mechanisms that generate the prediction, making even accurate predictions difficult to interpret and validate. In critical contexts, predictive accuracy alone is not a sufficient validation metric if the reasons underlying model decisions remain unexplained.

摘要： 在预测建模中，解释模型为何产生特定目标预测的能力已变得日益重要 [5, 10]。黑盒模型无法提供生成预测的内部机制的透明描述，这使得即使是准确的预测也难以解释和验证。在关键应用场景中，如果模型决策背后的原因无法得到解释，仅凭预测准确性不足以作为验证指标。

---

The IMEX (Interaction-Based Model Explanation) approach represents a methodological direction within explainable predictive modeling. IMEX is designed to identify which variables contribute most to the target prediction and which interactions among variables are significant in determining the target. The method does not impose limitations on higher-order interaction analysis, allowing the investigation of feature subsets with cardinality greater than two.

IMEX（基于交互的模型解释）方法代表了可解释预测建模领域的一种方法论方向。IMEX 旨在识别哪些变量对目标预测的贡献最大，以及变量间的哪些交互作用对确定目标具有显著影响。该方法不对高阶交互分析施加限制，允许研究基数大于 2 的特征子集。

---

Beyond the identification of feature importance, IMEX enables the exploration of interaction patterns that may be consistent with latent mechanisms influencing the outcome. Through the application of the IMEX algorithm, it is possible to construct an interpretability map of the predictions. The IMEX framework is built on two complementary metrics: Static Correlation Power (PCS), which quantifies the contribution of individual features, and Interaction Correlation Power (PCI), which captures non-additive effects among features.

除了识别特征重要性之外，IMEX 还能够探索可能与影响结果的潜在机制相一致的交互模式。通过应用 IMEX 算法，可以构建预测的可解释性图谱。IMEX 框架建立在两个互补的指标之上：静态相关能力（PCS），用于量化单个特征的贡献；以及交互相关能力（PCI），用于捕捉特征间的非加性效应。

---

In the present work, the PCS component is experimentally validated through a comparison with INVASE [18] on three synthetic datasets with known structures. The results indicate that IMEX can recover relevant feature-level structures in the presence of non-linear, conditional, and multicollinear relationships between input features and prediction targets.

在本文中，PCS 组件通过与 INVASE [18] 在三个具有已知结构的合成数据集上的对比进行了实验验证。结果表明，即使在输入特征与预测目标之间存在非线性、条件性和多重共线性关系的情况下，IMEX 仍能恢复相关的特征级结构。