提出ϕ-表，让全局SHAP解释更全面可靠
$ϕ$-Table: A Statistical Explanation for Global SHAP
- 用SHAP选特征，再拟合标准化线性代理模型
- 同时报告影响方向、不确定性、模型拟合度和系数稳定性
- 适合需要可解释性统计验证的研究者使用
全局SHAP解释通常只给出特征重要性排序，无法反映变量效应的方向性、不确定性及对模型响应的忠实程度。本文提出ϕ-表，一种基于SHAP的统计解释表格，适用于表格型黑箱回归模型。该方法通过SHAP重要性筛选特征，并对拟合模型响应𝑓(𝑋) 拟合标准化线性代理模型，输出SHAP重要性、模型响应系数、不确定性摘要、代理模型拟合度以及系数的自助法稳定性。所得系数可解释为模型响应在所选特征集上的投影。在合成数据、半合成数据与真实数据实验中，ϕ-表将仅含排序的SHAP扩展为包含方向性、不确定性、拟合度与稳定性的统计解释，全面揭示模型行为。
原文摘要 · Abstract (English)
Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but do not indicate whether their effects admit clear directional summaries, how uncertain those summaries are, or how faithfully they represent the fitted response. This paper proposes the $ϕ$-table, a SHAP-based statistical explanation table for tabular black-box regression models. The procedure selects features by SHAP importance and fits a standardized linear surrogate to the fitted model response $f(X)$, reporting SHAP importance together with model-response coefficients, uncertainty summaries, surrogate fidelity, and bootstrap coefficient stability. The resulting coefficients are interpreted as projections of the fitted model response onto the SHAP-selected feature set. Across synthetic, semi-synthetic, and real-data experiments, the $ϕ$-table extends ranking-only SHAP into a statistical global explanation by exposing direction, uncertainty, fidelity, and stability as distinct components of fitted model behavior.
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。