arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2507.04490cs.LGcs.AIstat.ML
收藏

在上下文异常检测中处理不确定性

Dealing with Uncertainty in Contextual Anomaly Detection

AI Lab, Department of Information Engineering University of Florence(人工智能实验室,信息工程系,佛罗伦萨大学);DTAI Research Unit, Department of Computer Science & Leuven.AI KU Leuven(DTAI研究单位,计算机科学系及Leuven.AI,根特大学);Cardiology Service CMSR Veneto Medica, Italy(心脏科服务CMSR威尼斯医疗集团,意大利)

Luca Bindini, Lorenzo Perini, Stefano Nistri, Jesse Davis, Paolo Frasconi

AI总结:

本文提出了一种基于异方差高斯过程回归的正常性分数框架,用于在上下文异常检测中建模和处理aleatoric和epistemic不确定性,以提高检测准确性和可解释性。

摘要:

上下文异常检测(CAD)旨在根据一组影响目标变量正常性的上下文变量,识别目标(行为)变量中的异常。在许多异常检测任务中,存在一些影响目标变量正常性的上下文变量,但这些变量本身并不是异常的指示器。在本工作中,我们提出了一种新的CAD框架,即正常性分数(NS),它明确建模了aleatoric和epistemic不确定性。基于异方差高斯过程回归,我们的方法将Z分数视为随机变量,提供反映异常评估可靠性的置信区间。通过在基准数据集和心脏病学中的实际应用实验,我们证明NS在检测准确性和可解释性方面均优于最先进的CAD方法。此外,置信区间使能够进行适应性的、基于不确定性的决策过程,这在如医疗领域等可能非常重要。

英文摘要:

Contextual anomaly detection (CAD) aims to identify anomalies in a target (behavioral) variable conditioned on a set of contextual variables that influence the normalcy of the target variable but are not themselves indicators of anomaly. In many anomaly detection tasks, there exist contextual variables that influence the normalcy of the target variable but are not themselves indicators of anomaly. In this work, we propose a novel framework for CAD, normalcy score (NS), that explicitly models both the aleatoric and epistemic uncertainties. Built on heteroscedastic Gaussian process regression, our method regards the Z-score as a random variable, providing confidence intervals that reflect the reliability of the anomaly assessment. Through experiments on benchmark datasets and a real-world application in cardiology, we demonstrate that NS outperforms state-of-the-art CAD methods in both detection accuracy and interpretability. Moreover, confidence intervals enable an adaptive, uncertainty-driven decision-making process, which may be very important in domains such as healthcare.

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。

↑