AnomalyGFM：面向零样本/少样本异常检测的图基础模型
AnomalyGFM: Graph Foundation Model for Zero/Few-shot Anomaly Detection
AI总结：
本文提出图基础模型AnomalyGFM，通过将可学习的正常/异常类原型与节点表示残差对齐，学习图无关的判别性原型，从而在零样本和少样本设置下实现跨图异常检测，并在11个数据集上显著优于现有方法。
摘要：
图异常检测（GAD）旨在识别图中与大多数节点不同的异常节点，近年来引起了广泛关注。现有的通用图模型在不同的图任务中取得了显著成功，但难以泛化到GAD任务。这一局限性源于它们难以学习到能够捕捉来自不同领域的图中固有的低频、不规则和异质性异常模式的通用知识。为应对这一挑战，我们提出了AnomalyGFM，一个面向GAD的图基础模型，支持在多样化的图数据集上对GAD进行零样本推理和少样本提示微调。一个关键见解是，需要与图无关的正常类和异常类表示，以支持跨不同图的有效零样本/少样本GAD。受此启发，AnomalyGFM在预训练阶段将数据无关的、可学习的正常类和异常类原型与节点表示残差（即节点相对于其邻居的表示偏差）进行对齐。残差特征本质上将节点信息投影到一个统一的特征空间中，在该空间中我们可以以一致的方式有效度量来自不同图的节点的异常程度。这为学习与图无关的、具有判别力的正常类和异常类原型提供了驱动力，这些原型可用于在新图上实现零样本GAD，包括超大规模图。如果新图中存在少量带标签的正常节点，AnomalyGFM还可以进一步支持提示微调，以利用这些节点实现更好的适应。在11个广泛使用的包含真实异常的GAD数据集上的综合实验表明，AnomalyGFM在零样本和少样本GAD设置下均显著优于最先进的竞争方法。
英文摘要：
Graph anomaly detection (GAD) aims to identify abnormal nodes that differ from the majority of the nodes in a graph, which has been attracting significant attention in recent years. Existing generalist graph models have achieved remarkable success in different graph tasks but struggle to generalize to the GAD task. This limitation arises from their difficulty in learning generalized knowledge for capturing the inherently infrequent, irregular and heterogeneous abnormality patterns in graphs from different domains. To address this challenge, we propose AnomalyGFM, a GAD-oriented graph foundation model that supports zero-shot inference and few-shot prompt tuning for GAD in diverse graph datasets. One key insight is that graph-agnostic representations for normal and abnormal classes are required to support effective zero/few-shot GAD across different graphs. Motivated by this, AnomalyGFM is pre-trained to align data-independent, learnable normal and abnormal class prototypes with node representation residuals (i.e., representation deviation of a node from its neighbors). The residual features essentially project the node information into a unified feature space where we can effectively measure the abnormality of nodes from different graphs in a consistent way. This provides a driving force for the learning of graph-agnostic, discriminative prototypes for the normal and abnormal classes, which can be used to enable zero-shot GAD on new graphs, including very large-scale graphs. If there are few-shot labeled normal nodes available in the new graphs, AnomalyGFM can further support prompt tuning to leverage these nodes for better adaptation. Comprehensive experiments on 11 widely-used GAD datasets with real anomalies, demonstrate that AnomalyGFM significantly outperforms state-of-the-art competing methods under both zero- and few-shot GAD settings.
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。
