arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.11223stat.MLcs.AIcs.LG
收藏

区域解释:连接局部和全局变量重要性

Regional Explanations: Bridging Local and Global Variable Importance

J.P. Morgan AI Research(摩根大通人工智能研究院);LaMME, ENSIIE, University Paris Saclay(巴黎萨克雷大学ENSIIE LaMME实验室);Capgemini Invent(凯捷创新)

Salim I. Amoukou, Nicolas J-B. Brunel

AI总结:

本文分析了局部归因方法Local Shapley Values和LIME的局限性,提出R-LOCO方法通过区域划分提升归因准确性,实现局部与全局解释的结合。

摘要:

我们分析了两种广泛使用的局部归因方法,Local Shapley Values和LIME,旨在量化特征值$x_i$对特定预测$f(x_1, \dots, x_p)$的贡献。尽管广泛应用,我们发现其在理想条件下仍无法可靠检测局部重要特征。我们认为,合理的局部归因方法不应赋予那些不影响模型输出(如线性模型中系数为零的特征)或与功能相关特征无统计依赖的特征重要性。我们证明Local SV和LIME违反这一基本原理。为此,我们提出R-LOCO(区域留出协变量),通过将输入空间划分为具有相似特征重要性特征的区域,应用全局归因方法,从区域成员身份推导实例的特征贡献。此方法提供更忠实的局部归因,避免局部解释不稳定性,并保留全局方法常丢失的实例特定细节。

英文摘要:

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.

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。

↑