FLEX：基于分层反事实解释的特征重要性
FLEX: Feature Importance from Layered Counterfactual Explanations
AI总结：
针对现有反事实解释仅适配单实例、无法支撑多尺度特征重要性量化的问题，提出模型无关的FLEX框架，可生成本地、区域、全局三级特征重要性排名，兼顾适配性与解释全面性。
摘要：
机器学习模型在各领域均取得了当前最优性能，但可解释性的缺失限制了其在高风险场景下的安全部署。反事实解释被广泛用于提供可操作的“假设性”追索方案，但这类解释通常仅针对单个实例，无法量化在特征空间的连贯区域内或整个数据集上，哪些特征会系统性地驱动结果变化。我们提出FLEX（基于分层反事实解释的特征重要性），这是一个与模型和领域无关的框架，可将多组反事实转换为局部、区域和全局三个层级的特征变化频率得分。FLEX通过跨实例和邻域聚合的方式，对局部变化频率度量进行泛化，提供可解释的特征排名，反映每个特征需要发生变化以翻转预测结果的频率。该框架兼容不同的反事实生成方法，允许用户侧重稀疏性、可行性或可操作性等特性，从而根据实际约束调整推导得到的特征重要性。我们在交通事故严重程度预测和贷款审批两个差异显著的表格任务上评估FLEX，并将其与SHAP和LIME推导的特征重要性值进行对比。结果显示：（i）FLEX的全局排名与SHAP具有相关性，同时能发现额外的驱动因素；（ii）区域分析可揭示全局汇总遗漏的场景特定因素。FLEX因此弥合了局部追索与全局归因之间的差距，可在风险敏感应用中支持透明、面向干预的决策。
英文摘要：
Machine learning models achieve state-of-the-art performance across domains, yet their lack of interpretability limits safe deployment in high-stakes settings. Counterfactual explanations are widely used to provide actionable "what-if" recourse, but they typically remain instance-specific and do not quantify which features systematically drive outcome changes within coherent regions of the feature space or across an entire dataset. We introduce FLEX (Feature importance from Layered counterfactual EXplanations), a model- and domain-agnostic framework that converts sets of counterfactuals into feature change frequency scores at local, regional, and global levels. FLEX generalises local change-frequency measures by aggregating across instances and neighbourhoods, offering interpretable rankings that reflect how often each feature must change to flip predictions. The framework is compatible with different counterfactual generation methods, allowing users to emphasise characteristics such as sparsity, feasibility, or actionability, thereby tailoring the derived feature importances to practical constraints. We evaluate FLEX on two contrasting tabular tasks: traffic accident severity prediction and loan approval, and compare FLEX to SHAP- and LIME-derived feature importance values. Results show that (i) FLEX's global rankings correlate with SHAP while surfacing additional drivers, and (ii) regional analyses reveal context-specific factors that global summaries miss. FLEX thus bridges the gap between local recourse and global attribution, supporting transparent and intervention-oriented decision-making in risk-sensitive applications.
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。
