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 2603.29183cs.LGcs.AI
收藏

IMPACT: 开集时间序列异常检测中的影响建模

IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection

National Key Laboratory of Parallel and Distributed Computing(国家级并行与分布式计算实验室);College of Computer Science and Technology, National University of Defense Technology(国防科技大学计算机科学与技术学院);Intelligent Game and Decision Lab (IGDL)(智能游戏与决策实验室(IGDL));Information Systems Technology and Design, Singapore University of Technology and Design(新加坡科技设计大学信息系统技术与设计系);School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算与信息系统学院)

Xiaohui Zhou, Yijie Wang, Hongzuo Xu, Weixuan Liang, Xiaoli Li, Guansong Pang

AI总结:

本文提出IMPACT框架,通过影响建模方法解决开集时间序列异常检测中的挑战,通过学习影响函数生成真实异常模式并净化训练数据。

摘要:

开集异常检测(OSAD)是一种新兴范式,旨在利用训练中观察到的异常类有限标记数据,在测试时识别已见和未见的异常。当前方法依赖简单的增强方法生成伪异常以复制未见异常。尽管在图像数据中表现良好,但这些方法在时间序列数据中效果不佳,因为未能保持其序列特性,导致异常模式变得琐碎或不真实。当训练数据被未标记异常污染时,问题进一步加剧。本文引入IMPACT,一种新的框架,利用影响建模方法解决这些挑战。关键见解是学习一个影响函数,以准确估计单个训练样本对建模的影响,然后利用这些影响分数生成语义上不同但真实的未见异常,同时将高影响样本重新利用为监督异常以净化数据。大量实验表明,IMPACT显著优于现有最先进方法,在各种OSAD设置和污染率下表现出更高的准确性。代码可在https://github.com/mala-lab/IMPACT获取。

英文摘要:

Open-set anomaly detection (OSAD) is an emerging paradigm designed to utilize limited labeled data from anomaly classes seen in training to identify both seen and unseen anomalies during testing. Current approaches rely on simple augmentation methods to generate pseudo anomalies that replicate unseen anomalies. Despite being promising in image data, these methods are found to be ineffective in time series data due to the failure to preserve its sequential nature, resulting in trivial or unrealistic anomaly patterns. They are further plagued when the training data is contaminated with unlabeled anomalies. This work introduces $\textbf{IMPACT}$, a novel framework that leverages $\underline{\textbf{i}}$nfluence $\underline{\textbf{m}}$odeling for o$\underline{\textbf{p}}$en-set time series $\underline{\textbf{a}}$nomaly dete$\underline{\textbf{ct}}$ion, to tackle these challenges. The key insight is to $\textbf{i)}$ learn an influence function that can accurately estimate the impact of individual training samples on the modeling, and then $\textbf{ii)}$ leverage these influence scores to generate semantically divergent yet realistic unseen anomalies for time series while repurposing high-influential samples as supervised anomalies for anomaly decontamination. Extensive experiments show that IMPACT significantly outperforms existing state-of-the-art methods, showing superior accuracy under varying OSAD settings and contamination rates. Code is available at https://github.com/mala-lab/IMPACT.

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。

↑