VARSHAP用方差减少量衡量特征重要性，更准确捕捉局部模型行为。
VARSHAP: Addressing Global Dependency Problems in Explainable AI with Variance-Based Local Feature Attribution
- 以预测方差减少量作为特征重要性指标，基于Shapley值框架改进。
- 在合成与真实数据集上优于KernelSHAP和LIME，尤其对数据分布变化鲁棒。
- 适合需要高可信度局部解释的场景，如医疗或金融决策分析。
现有特征归因方法如SHAP常受全局依赖性影响，无法准确反映局部模型行为。本文提出VARSHAP，一种新型模型无关的局部特征归因方法，以预测方差的减少量作为特征重要性的核心度量。基于Shapley值框架，VARSHAP满足关键Shapley公理，但相较于SHAP，对全局数据分布变化更具鲁棒性。在合成数据与真实世界数据集上的实验表明，VARSHAP在定量与定性层面均优于KernelSHAP、LIME等主流方法。
原文摘要 · Abstract (English)
Existing feature attribution methods like SHAP often suffer from global dependence, failing to capture true local model behavior. This paper introduces VARSHAP, a novel model-agnostic local feature attribution method which uses the reduction of prediction variance as the key importance metric of features. Building upon Shapley value framework, VARSHAP satisfies the key Shapley axioms, but, unlike SHAP, is resilient to global data distribution shifts. Experiments on synthetic and real-world datasets demonstrate that VARSHAP outperforms popular methods such as KernelSHAP or LIME, both quantitatively and qualitatively.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。