ARC：一种具备上下文学习的通用图异常检测器
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
AI总结：
本文提出ARC，一种基于上下文学习的通用图异常检测器，通过特征对齐、残差图编码和交叉注意力异常评分三个模块，实现无需重训练即可跨数据集即时检测异常，显著提升了泛化性和效率。
摘要：
图异常检测（GAD）旨在识别图中与多数节点不同的异常节点，已引起广泛关注。然而，现有的GAD方法需要针对每个数据集进行特定训练，导致训练成本高、数据需求大，且在应用于新数据集和领域时泛化能力有限。为解决这些局限，本文提出ARC，一种通用GAD方法，使“一模型适用所有”的GAD模型能够即时检测各种图数据集中的异常。借助上下文学习，ARC可在推理阶段利用少样本正常样本直接从目标数据集提取特定模式，无需在目标数据集上重新训练或微调。ARC包含三个精心设计的组件以捕捉通用图异常模式：1）基于平滑性的特征对齐模块，将不同数据集的特征统一到共同的异常敏感空间；2）自我-邻居残差图编码器，学习与异常相关的节点嵌入；3）交叉注意力上下文异常评分模块，利用少样本正常样本预测节点异常。在多个领域的基准数据集上的大量实验表明，ARC具有卓越的异常检测性能、效率和泛化能力。
英文摘要：
Graph anomaly detection (GAD), which aims to identify abnormal nodes that differ from the majority within a graph, has garnered significant attention. However, current GAD methods necessitate training specific to each dataset, resulting in high training costs, substantial data requirements, and limited generalizability when being applied to new datasets and domains. To address these limitations, this paper proposes ARC, a generalist GAD approach that enables a ``one-for-all'' GAD model to detect anomalies across various graph datasets on-the-fly. Equipped with in-context learning, ARC can directly extract dataset-specific patterns from the target dataset using few-shot normal samples at the inference stage, without the need for retraining or fine-tuning on the target dataset. ARC comprises three components that are well-crafted for capturing universal graph anomaly patterns: 1) smoothness-based feature Alignment module that unifies the features of different datasets into a common and anomaly-sensitive space; 2) ego-neighbor Residual graph encoder that learns abnormality-related node embeddings; and 3) cross-attentive in-Context anomaly scoring module that predicts node abnormality by leveraging few-shot normal samples. Extensive experiments on multiple benchmark datasets from various domains demonstrate the superior anomaly detection performance, efficiency, and generalizability of ARC.
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。
