提出新方法R-LOCO，让局部解释更准确可靠。
Regional Explanations: Bridging Local and Global Variable Importance
- 用区域分组思想融合全局与局部解释
- 在理想条件下仍能准确识别关键特征
- 适合需要可信解释的机器学习应用
我们分析了两种广泛使用的局部归因方法：局部Shapley值（Local Shapley Values）和LIME，它们旨在量化某个特征值 $x_i$ 对特定预测 $f(x_1, \dots, x_p)$ 的贡献。尽管应用广泛，我们发现即使在精确计算且特征独立的理想条件下，这两种方法仍无法可靠检测局部重要特征。我们认为，一个合理的局部归因方法不应赋予那些既不影响模型输出（如线性模型中系数为零的特征），也不与功能相关特征存在统计依赖性的特征重要性。我们证明，局部SV和LIME均违反此基本原则。为此，我们提出R-LOCO（Regional Leave Out COvariates），它在局部与全局解释之间建立桥梁，提供更准确的归因结果。R-LOCO将输入空间划分为具有相似特征重要性特征的区域，并在这些区域内应用全局归因方法，通过实例所属区域推导其特征贡献。该方法在避免局部解释不稳定性的同时，保留了全局方法常丢失的实例特异性细节。
原文摘要 · Abstract (English)
We analyze two widely used local attribution methods, Local Shapley Values and LIME, which aim to quantify the contribution of a feature value $x_i$ to a specific prediction $f(x_1, \dots, x_p)$. Despite their widespread use, we identify fundamental limitations in their ability to reliably detect locally important features, even under ideal conditions with exact computations and independent features. We argue that a sound local attribution method should not assign importance to features that neither influence the model output (e.g., features with zero coefficients in a linear model) nor exhibit statistical dependence with functionality-relevant features. We demonstrate that both Local SV and LIME violate this fundamental principle. To address this, we propose R-LOCO (Regional Leave Out COvariates), which bridges the gap between local and global explanations and provides more accurate attributions. R-LOCO segments the input space into regions with similar feature importance characteristics. It then applies global attribution methods within these regions, deriving an instance's feature contributions from its regional membership. This approach delivers more faithful local attributions while avoiding local explanation instability and preserving instance-specific detail often lost in global methods.
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。