arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.11933cs.LGcs.SI
收藏

SLADE:通过自监督学习在无标签的边流中检测动态异常

SLADE: Detecting Dynamic Anomalies in Edge Streams without Labels via Self-Supervised Learning

KAIST(韩国科学技术院)

Jongha Lee, Sunwoo Kim, Kijung Shin

AI总结:

提出自监督框架SLADE,通过训练神经网络最小化节点表示漂移并从短期模式生成长期模式,在无标签边流中实现常数时间的动态异常检测,性能优于多种有监督方法。

摘要:

为了检测社交、电子邮件和金融网络等真实世界图中的异常,人们已经开发了各种方法。尽管这些方法通常假设输入图是静态的,但大多数真实世界的图会随时间增长,自然地表示为边流。在此背景下,我们旨在实现三个目标:(a) 在异常发生时立即检测,(b) 适应动态变化的状态,以及 (c) 处理动态异常标签的稀缺性。在本文中,我们提出了SLADE(边流异常检测的自监督学习),用于在不依赖标签的情况下快速检测边流中的动态异常。SLADE通过观察节点交互模式随时间的偏差来检测节点向异常状态的转变。为此,它训练一个深度神经网络来执行两个自监督任务:(a) 最小化节点表示的漂移,以及 (b) 从短期交互模式生成长期交互模式。节点在这些任务上的失败表明其偏离了常态。值得注意的是,神经网络和任务经过精心设计,使得所有必需的操作都可以在常数时间内(相对于图大小)响应输入流中的每条新边。在四个真实世界数据集上的动态异常检测中,SLADE优于九种竞争方法,甚至包括那些利用标签监督的方法。

英文摘要:

To detect anomalies in real-world graphs, such as social, email, and financial networks, various approaches have been developed. While they typically assume static input graphs, most real-world graphs grow over time, naturally represented as edge streams. In this context, we aim to achieve three goals: (a) instantly detecting anomalies as they occur, (b) adapting to dynamically changing states, and (c) handling the scarcity of dynamic anomaly labels. In this paper, we propose SLADE (Self-supervised Learning for Anomaly Detection in Edge Streams) for rapid detection of dynamic anomalies in edge streams, without relying on labels. SLADE detects the shifts of nodes into abnormal states by observing deviations in their interaction patterns over time. To this end, it trains a deep neural network to perform two self-supervised tasks: (a) minimizing drift in node representations and (b) generating long-term interaction patterns from short-term ones. Failure in these tasks for a node signals its deviation from the norm. Notably, the neural network and tasks are carefully designed so that all required operations can be performed in constant time (w.r.t. the graph size) in response to each new edge in the input stream. In dynamic anomaly detection across four real-world datasets, SLADE outperforms nine competing methods, even those leveraging label supervision.

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。

↑