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 2511.16482cs.LGcs.AIstat.ML
收藏

基于相关性的特征归因可解释人工智能

Correlation-Aware Feature Attribution Based Explainable AI

Department of Informatics, University of Oslo, Norway(奥斯陆大学信息学院)

Poushali Sengupta, Yan Zhang, Frank Eliassen, Sabita Maharjan

AI总结:

ExCIR通过相关性感知的归因方法,提供高效、一致且可扩展的可解释人工智能解决方案。

摘要:

可解释人工智能(XAI)随着现代模型变得更加复杂和高风险应用要求透明、信任和监管合规而变得越来越重要。现有全局归因方法往往计算成本高,缺乏在相关输入下的稳定性,并且无法有效扩展到大规模或异质数据集。我们通过ExCIR(通过相关性影响比率的可解释性)解决这些差距,这是一种相关性感知的归因分数,配备了轻量级的传输协议,仅使用数据集的一小部分即可重现完整模型的排名。ExCIR在经过稳健中心化(从特征和输出中减去稳健的定位估计,例如中位数或中位均值)后,量化了特征和模型输出之间的符号对齐共动。我们进一步引入BlockCIR,这是ExCIR的组级扩展,将相关特征集作为单个单元评分。通过在预定义或数据驱动的组上聚合相同的符号共动分子和幅度,BlockCIR在共线性簇(例如同义词或重复传感器)中减少双重计数,并在存在强依赖性时产生更平滑、更稳定的排名。在多样本文本、表格、信号和图像数据集上,ExCIR显示出与已建立的全局基线和完整模型的可信一致,提供在不同设置下的一致前k排名,并通过在数据集子集上的轻量评估减少运行时间。总体而言,ExCIR为实际应用提供了计算高效、一致和可扩展的可解释性。

英文摘要:

Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing global attribution methods often incur high computational costs, lack stability under correlated inputs, and fail to scale efficiently to large or heterogeneous datasets. We address these gaps with \emph{ExCIR} (Explainability through Correlation Impact Ratio), a correlation-aware attribution score equipped with a lightweight transfer protocol that reproduces full-model rankings using only a fraction of the data. ExCIR quantifies sign-aligned co-movement between features and model outputs after \emph{robust centering} (subtracting a robust location estimate, e.g., median or mid-mean, from features and outputs). We further introduce \textsc{BlockCIR}, a \emph{groupwise} extension of ExCIR that scores \emph{sets} of correlated features as a single unit. By aggregating the same signed-co-movement numerators and magnitudes over predefined or data-driven groups, \textsc{BlockCIR} mitigates double-counting in collinear clusters (e.g., synonyms or duplicated sensors) and yields smoother, more stable rankings when strong dependencies are present. Across diverse text, tabular, signal, and image datasets, ExCIR shows trustworthy agreement with established global baselines and the full model, delivers consistent top-$k$ rankings across settings, and reduces runtime via lightweight evaluation on a subset of rows. Overall, ExCIR provides \emph{computationally efficient}, \emph{consistent}, and \emph{scalable} explainability for real-world deployment.

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。

↑