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 2205.13845cs.LGcs.AI
收藏

提高图级异常检测的标准

Raising the Bar in Graph-level Anomaly Detection

Bosch Center for Artificial Intelligence(博世人工智能中心);TU Kaiserslautern(凯泽斯劳滕工业大学);University of California, Irvine(加州大学欧文分校)

Chen Qiu, Marius Kloft, Stephan Mandt, Maja Rudolph

摘要:

图级异常检测已成为金融欺诈检测和社交网络异常活动检测等多个领域的重要课题。虽然大多数研究都集中在视觉数据(如图像)的异常检测上,其中已经获得了高检测精度,但现有的用于图形的深度学习方法目前表现出相当差的性能。本文提出了图级异常检测的标准,即,在一组图中检测异常图的任务。通过借鉴自监督学习和转换学习的思想,我们提出了一种新的深度学习方法,通过修复现有的深度单类方法的一些已知问题,包括超球崩溃和性能翻转,显着改善了现有的深度单类方法。在涉及9种技术的9个真实数据集上的实验表明,与现有的最佳方法相比,我们的方法实现了11.8%AUC的平均性能提高。

英文摘要:

Graph-level anomaly detection has become a critical topic in diverse areas, such as financial fraud detection and detecting anomalous activities in social networks. While most research has focused on anomaly detection for visual data such as images, where high detection accuracies have been obtained, existing deep learning approaches for graphs currently show considerably worse performance. This paper raises the bar on graph-level anomaly detection, i.e., the task of detecting abnormal graphs in a set of graphs. By drawing on ideas from self-supervised learning and transformation learning, we present a new deep learning approach that significantly improves existing deep one-class approaches by fixing some of their known problems, including hypersphere collapse and performance flip. Experiments on nine real-world data sets involving nine techniques reveal that our method achieves an average performance improvement of 11.8% AUC compared to the best existing approach.

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。

↑