PREM：一种简单而有效的节点级图异常检测方法
PREM: A Simple Yet Effective Approach for Node-Level Graph Anomaly Detection
AI总结：
本文提出PREM方法，通过预处理与自我-邻居匹配模块及简单对比损失，在保持节点级图异常检测性能的同时显著提升训练效率并降低内存消耗。
摘要：
节点级图异常检测（GAD）在医学、社交网络和电子商务等多个领域中，对于从图结构数据中识别异常节点起着关键作用。然而，由于异常的多样性以及标注数据的匮乏，该任务面临诸多挑战。现有方法——基于重构和基于对比学习的方法——虽然有效，但往往因其复杂的目标函数和精细的模块设计而存在效率问题。为了提高GAD的效率，我们提出了一种简单的方法，称为预处理与匹配（简称PREM）。我们的方法简化了GAD流程，在保持强大异常检测能力的同时，减少了时间和内存消耗。PREM由两个模块组成——一个预处理模块和一个自我-邻居匹配模块——它消除了训练期间进行消息传递传播的必要性，并采用简单的对比损失，从而显著减少了训练时间和内存占用。此外，通过在五个真实世界数据集上的严格评估，我们的方法展示了鲁棒性和有效性。值得注意的是，在ACM数据集上验证时，与最高效的基线方法相比，PREM的AUC提高了5%，训练速度提升了9倍，并大幅降低了内存使用。
英文摘要：
Node-level graph anomaly detection (GAD) plays a critical role in identifying anomalous nodes from graph-structured data in various domains such as medicine, social networks, and e-commerce. However, challenges have arisen due to the diversity of anomalies and the dearth of labeled data. Existing methodologies - reconstruction-based and contrastive learning - while effective, often suffer from efficiency issues, stemming from their complex objectives and elaborate modules. To improve the efficiency of GAD, we introduce a simple method termed PREprocessing and Matching (PREM for short). Our approach streamlines GAD, reducing time and memory consumption while maintaining powerful anomaly detection capabilities. Comprising two modules - a pre-processing module and an ego-neighbor matching module - PREM eliminates the necessity for message-passing propagation during training, and employs a simple contrastive loss, leading to considerable reductions in training time and memory usage. Moreover, through rigorous evaluations of five real-world datasets, our method demonstrated robustness and effectiveness. Notably, when validated on the ACM dataset, PREM achieved a 5% improvement in AUC, a 9-fold increase in training speed, and sharply reduce memory usage compared to the most efficient baseline.
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。
