基于交互的模型解释
IMEX Interaction-Based Model Explanation
- Backwell Tech Corp. Europe GmbH（Backwell科技欧洲有限公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
研究聚焦于预测建模中黑箱模型难以解释的问题，提出IMEX方法，通过两个互补指标识别变量贡献及交互，经实验验证可在复杂关系下恢复特征级结构，构建预测的可解释性图。
AI中文摘要：
在预测建模中，解释模型为何产生给定目标预测的能力愈发重要。黑箱模型难以解释预测机制。IMEX方法是可解释预测建模的一个方向，旨在识别对目标预测贡献最大的变量及变量间的重要交互，不限高阶交互分析。通过IMEX算法可构建预测的可解释性图。该框架基于两个互补指标，PCS量化单个特征贡献，PCI捕捉特征间非加性效应。通过与INVASE在三个合成数据集上比较，实验验证了PCS组件，结果表明IMEX能在存在多种复杂关系时恢复相关特征级结构。
英文摘要：
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. 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. 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. 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.
