基于多尺度对比学习的正态性学习图异常检测
Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning
AI总结：
针对图异常检测任务中对任务特性研究不足的问题，提出基于正态性学习的多尺度对比学习框架NLGAD，通过多尺度对比初始化、混合正态节点选择和仅用正常节点微调的方式，在6个基准数据集上取得最高5.89%的AUC提升。
摘要：
图异常检测（GAD）在机器学习与数据挖掘领域受到越来越多的关注。现有研究主要聚焦于如何捕获更丰富的信息以提升GAD任务的节点嵌入质量。尽管这些工作在检测性能上已取得显著进展，但针对该任务本身特性的研究仍相对匮乏。GAD的目标是识别出偏离大多数节点的异常点。然而，模型往往容易学习到占样本绝大多数的正常样本的模式；同时，当异常节点的行为与正态模式存在差异时，也更容易被检测出来。因此，增强模型对正常模式的学习能力可进一步提升检测性能。为此，我们提出一种基于正态性学习的多尺度对比学习网络GAD框架（缩写为NLGAD）。具体而言，我们首先利用不同尺度的对比网络初始化模型。为了给正态性学习提供充足且可靠的正常节点，我们设计了一种有效的混合正态性选择策略。最后，仅以可靠的正常节点作为输入对模型进行微调，使其学习到更准确的正态性估计，从而更易区分异常节点。最终，在6个基准图数据集上的大量实验证明了我们基于正态性学习的方案在GAD任务上的有效性。值得注意的是，与现有最优方法相比，所提算法提升了检测性能，AUC增益最高达5.89%。源代码已发布于https://github.com/FelixDJC/NLGAD。
英文摘要：
Graph anomaly detection (GAD) has attracted increasing attention in machine learning and data mining. Recent works have mainly focused on how to capture richer information to improve the quality of node embeddings for GAD. Despite their significant advances in detection performance, there is still a relative dearth of research on the properties of the task. GAD aims to discern the anomalies that deviate from most nodes. However, the model is prone to learn the pattern of normal samples which make up the majority of samples. Meanwhile, anomalies can be easily detected when their behaviors differ from normality. Therefore, the performance can be further improved by enhancing the ability to learn the normal pattern. To this end, we propose a normality learning-based GAD framework via multi-scale contrastive learning networks (NLGAD for abbreviation). Specifically, we first initialize the model with the contrastive networks on different scales. To provide sufficient and reliable normal nodes for normality learning, we design an effective hybrid strategy for normality selection. Finally, the model is refined with the only input of reliable normal nodes and learns a more accurate estimate of normality so that anomalous nodes can be more easily distinguished. Eventually, extensive experiments on six benchmark graph datasets demonstrate the effectiveness of our normality learning-based scheme on GAD. Notably, the proposed algorithm improves the detection performance (up to 5.89% AUC gain) compared with the state-of-the-art methods. The source code is released at https://github.com/FelixDJC/NLGAD.
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。
