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 2410.18487cs.LG
收藏

图预训练模型是强大的异常检测器

Graph Pre-Training Models Are Strong Anomaly Detectors

HKUST(香港科技大学);HKUST (GZ)(香港科技大学(广州));Tencent AI Lab(腾讯AI实验室);DAMO Academy, Alibaba Group(阿里巴巴达摩院)

Jiashun Cheng, Zinan Zheng, Yang Liu, Jianheng Tang, Hongwei Wang, Yu Rong, Jia Li, Fugee Tsung

AI总结:

本文研究图预训练在GAD中的作用,证明其在有限监督下显著优于端到端GNN,并揭示其对远距离、少样本无标注异常的检测优势。

摘要:

图异常检测(GAD)是一个具有挑战性且实用的研究课题,图神经网络(GNN)近期已在该领域展现出良好效果。现有GNN在GAD中的有效性主要归因于以端到端方式同时学习节点表示和分类器。与此同时,图预训练作为DGI、GraphMAE等两阶段学习范式,已显示出利用无标注图数据增强下游任务的潜力,但其对GAD的影响仍未得到充分研究。本文表明,图预训练模型是强大的图异常检测器。具体而言,我们证明预训练具有很强竞争力,在监督有限时显著优于最先进的端到端训练模型。为理解这一现象,我们进一步揭示预训练增强了对已知异常2跳邻域之外、距离较远、代表性不足且无标注异常的检测,从而解释其相较端到端模型的优越性能。此外,我们还将考察扩展到预训练在图级异常检测中的潜力。我们期望本文能推动重新评估预训练在GAD中的作用,并为未来研究提供有价值的洞见。

英文摘要:

Graph Anomaly Detection (GAD) is a challenging and practical research topic where Graph Neural Networks (GNNs) have recently shown promising results. The effectiveness of existing GNNs in GAD has been mainly attributed to the simultaneous learning of node representations and the classifier in an end-to-end manner. Meanwhile, graph pre-training, the two-stage learning paradigm such as DGI and GraphMAE, has shown potential in leveraging unlabeled graph data to enhance downstream tasks, yet its impact on GAD remains under-explored. In this work, we show that graph pre-training models are strong graph anomaly detectors. Specifically, we demonstrate that pre-training is highly competitive, markedly outperforming the state-of-the-art end-to-end training models when faced with limited supervision. To understand this phenomenon, we further uncover pre-training enhances the detection of distant, under-represented, unlabeled anomalies that go beyond 2-hop neighborhoods of known anomalies, shedding light on its superior performance against end-to-end models. Moreover, we extend our examination to the potential of pre-training in graph-level anomaly detection. We envision this work to stimulate a re-evaluation of pre-training's role in GAD and offer valuable insights for future research.

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。

↑