[论文解读] An exact counterfactual-example-based approach to tree-ensemble models interpretability

Pierre Blanchart|arXiv (Cornell University)|May 31, 2021

Explainable Artificial Intelligence (XAI)参考文献 26被引用 6

一句话总结

本文提出了一种基于几何的精确方法，用于计算XGBoost和LightGBM等树集成模型的反事实解释，通过推导精确的多维区间来表征决策区域。该方法可实现最优反事实的精确计算，支持特征子集约束，并自然扩展至回归任务，为故障检测等高风险应用场景提供可解释、可操作的洞察。

ABSTRACT

Explaining the decisions of machine learning models is becoming a necessity in many areas where trust in ML models decision is key to their accreditation/adoption. The ability to explain models decisions also allows to provide diagnosis in addition to the model decision, which is highly valuable in scenarios such as fault detection. Unfortunately, high-performance models do not exhibit the necessary transparency to make their decisions fully understandable. And the black-boxes approaches, which are used to explain such model decisions, suffer from a lack of accuracy in tracing back the exact cause of a model decision regarding a given input. Indeed, they do not have the ability to explicitly describe the decision regions of the model around that input, which is necessary to determine what influences the model towards one decision or the other. We thus asked ourselves the question: is there a category of high-performance models among the ones currently used for which we could explicitly and exactly characterise the decision regions in the input feature space using a geometrical characterisation? Surprisingly we came out with a positive answer for any model that enters the category of tree ensemble models, which encompasses a wide range of high-performance models such as XGBoost, LightGBM, random forests ... We could derive an exact geometrical characterisation of their decision regions under the form of a collection of multidimensional intervals. This characterisation makes it straightforward to compute the optimal counterfactual (CF) example associated with a query point. We demonstrate several possibilities of the approach, such as computing the CF example based only on a subset of features. This allows to obtain more plausible explanations by adding prior knowledge about which variables the user can control. An adaptation to CF reasoning on regression problems is also envisaged.

研究动机与目标

• 为工业故障检测和异常检测中使用的高性能树集成模型缺乏准确、精确的解释问题提供解决方案。
• 开发一种显式利用多维区间表征输入空间中决策区域的方法，以支持精确的反事实推理。
• 通过支持用户控制的特征约束和部分反事实，提升现实场景中反事实的合理性与可解释性。
• 通过忠实建模外生变量与目标值之间的关系，将该方法扩展至回归问题。

提出的方法

• 将树集成模型的决策区域精确表征为输入空间中多维区间的集合（盒子）。
• 通过交集盒子递归限制特征空间，同时保持各维度上的最大覆盖范围和互不相交性。
• 通过在决策区域内寻找最小输入扰动以改变模型预测，来构建最优反事实示例。
• 通过在反事实搜索过程中固定不可控特征的取值，实现特征层面的约束，提升合理性。
• 利用树各层级之间的父子关系递归分解特征区间，确保方法的正确性与完备性。
• 通过定义将预测值移入用户指定目标区间的反事实，将方法扩展至回归问题，同时保持模型保真度。

实验结果

研究问题

• RQ1 能否使用输入空间中的几何区间精确表征树集成模型的决策区域？
• RQ2 能否利用这种几何表征精确且高效地计算最优反事实示例？
• RQ3 该方法能否支持尊重用户定义的特征约束（例如不可修改的变量）的反事实？
• RQ4 能否通过定义将预测值移入期望区间的反事实，将该方法适配至回归问题？
• RQ5 与近似黑箱反事实方法相比，该方法是否能提供更合理且可操作的解释？

主要发现

• 该方法将树集成模型的决策区域精确表征为互不相交且最大的多维区间。
• 通过在决策区域内寻找最小扰动以改变模型预测，精确计算出最优反事实示例。
• 通过固定不可控特征的取值，支持约束型反事实，从而生成更真实、更具可操作性的解释。
• 通过递归分解与区间交集性质，形式化证明了方法的正确性与完备性。
• 通过定义将预测值移入用户指定目标区间的反事实，该框架自然扩展至回归问题。
• 该方法通过显式揭示影响模型输出的决策边界，为任意给定输入提供完整的诊断洞察。