Abstract
Unsupervised graph anomaly detection aims at identifying rare patterns that deviate from the majority in a graph without the aid of labels, which is important for a variety of real-world applications. Recent advances have utilized Graph Neural Networks (GNNs) to learn effective node representations by aggregating information from neighborhoods. This is motivated by the hypothesis that nodes in the graph tend to exhibit consistent behaviors with their neighborhoods. However, such consistency can be disrupted by graph anomalies in multiple ways. Most existing methods directly employ GNNs to learn representations, disregarding the negative impact of graph anomalies on GNNs, resulting in sub-optimal node representations and anomaly detection performance. While a few recent approaches have redesigned GNNs for graph anomaly detection under semi-supervised label guidance, how to address the adverse effects of graph anomalies on GNNs in unsupervised scenarios and learn effective representations for anomaly detection are still under-explored. To bridge this gap, in this paper, we propose a simple yet effective framework for Guarding Graph Neural Networks for Unsupervised Graph Anomaly Detection (G3AD). Specifically, G3AD introduces two auxiliary networks along with correlation constraints to guard the GNNs from inconsistent information encoding. Furthermore, G3AD introduces an adaptive caching module to guard the GNNs from solely reconstructing the observed data that contains anomalies. Extensive experiments demonstrate that our proposed G3AD can outperform seventeen state-of-the-art methods on both synthetic and real-world datasets.
Abstract (translated)
无监督图异常检测旨在识别在图中与多数不同的罕见模式，而无需标签帮助，这对于各种现实应用场景具有重要意义。最近，人们利用图神经网络（GNNs）通过聚合图中的信息来学习有效的节点表示。这一假设基于一个结论，即图中节点通常会表现出与周围节点一致的行为。然而，图异常可能会以多种方式破坏这种一致性。大多数现有方法直接使用GNNs来学习表示，忽视了图异常对GNNs的负面影响，导致节点表示效果不佳和异常检测性能下降。虽然一些最近的方法为在半监督标签指导下去优化GNNs进行了重新设计，但如何解决图异常对GNNs在无监督场景下的不利影响以及如何学习有效的异常检测表示方法仍然是一个未探索的问题。为了填补这个空白，本文提出了一种简单的但有效的框架来保护无监督图神经网络免受异常的影响，即G3AD。具体来说，G3AD引入了两个辅助网络和相关约束来保护GNNs免受不一致信息编码。此外，G3AD还引入了自适应缓存模块来保护GNNs免受仅重构包含异常的观察数据。大量实验证明，我们提出的G3AD可以在 synthetic 和 real-world 数据上优于 17 个最先进的算法的表现。
URL
https://arxiv.org/abs/2404.16366
