反事实特征重要性值的计算与可视化
Calculating and Visualizing Counterfactual Feature Importance Values
AI总结：
针对反事实解释无法量化单特征影响、缺乏可视化工具的问题，提出两种CFI值计算方法与三类可视化图表，可增强反事实解释的信息性，且开源实现兼容各类反事实生成算法。
摘要：
尽管复杂机器学习算法凭借在预测任务中的出色表现取得了成功，但其固有的不透明性仍然对其负责任的应用构成挑战。反事实解释作为解释单个决策结果的一种潜在解决方案应运而生。然而，两个主要缺陷直接影响其可用性：（1）特征变化的同构视图，即无法观察到每个被修改的特征对预测的影响程度；（2）缺乏用于可视化反事实解释的图形资源。我们提出反事实特征（变化）重要性（Counterfactual Feature (change) Importance, CFI）值作为解决方案：一种为给定反事实解释中的每个特征变化分配重要性值的方法。为计算这些值，我们提出了两种潜在的CFI方法。一种方法简单、快速，具有贪心特性。另一种名为CounterShapley，提供了一种计算事实-反事实对之间Shapley值的方法。利用这些重要性值，我们还引入了三种图表类型来可视化反事实解释：（a）贪心图（Greedy chart），展示预测分数上升直至预测类别改变的贪心序贯路径；（b）CounterShapley图，在简单的一维图表中描绘其对应的分数；最后是（c）星座图（Constellation chart），展示特征变化的所有可能组合及其对模型预测分数的影响。对于我们提出的每一种CFI方法和可视化方案，我们都展示了它们如何能提供更多关于反事实解释的信息。最后，我们提供了一个开源实现，可与任何反事实解释生成算法兼容。代码仓库位于：https://github.com/ADMAntwerp/CounterPlots
英文摘要：
Despite the success of complex machine learning algorithms, mostly justified by an outstanding performance in prediction tasks, their inherent opaque nature still represents a challenge to their responsible application. Counterfactual explanations surged as one potential solution to explain individual decision results. However, two major drawbacks directly impact their usability: (1) the isonomic view of feature changes, in which it is not possible to observe \textit{how much} each modified feature influences the prediction, and (2) the lack of graphical resources to visualize the counterfactual explanation. We introduce Counterfactual Feature (change) Importance (CFI) values as a solution: a way of assigning an importance value to each feature change in a given counterfactual explanation. To calculate these values, we propose two potential CFI methods. One is simple, fast, and has a greedy nature. The other, coined CounterShapley, provides a way to calculate Shapley values between the factual-counterfactual pair. Using these importance values, we additionally introduce three chart types to visualize the counterfactual explanations: (a) the Greedy chart, which shows a greedy sequential path for prediction score increase up to predicted class change, (b) the CounterShapley chart, depicting its respective score in a simple and one-dimensional chart, and finally (c) the Constellation chart, which shows all possible combinations of feature changes, and their impact on the model's prediction score. For each of our proposed CFI methods and visualization schemes, we show how they can provide more information on counterfactual explanations. Finally, an open-source implementation is offered, compatible with any counterfactual explanation generator algorithm. Code repository at: https://github.com/ADMAntwerp/CounterPlots
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
