Reconstruction Enhanced Multi-View Contrastive Learning for Anomaly Detection on Attributed Networks
This addresses the problem of detecting abnormal nodes in networks for applications like fraud detection and cybersecurity, representing an incremental improvement over existing methods.
The paper tackles anomaly detection on attributed networks by proposing a self-supervised framework that combines multi-view contrastive learning and attribute reconstruction, achieving state-of-the-art performance on five benchmark datasets.
Detecting abnormal nodes from attributed networks is of great importance in many real applications, such as financial fraud detection and cyber security. This task is challenging due to both the complex interactions between the anomalous nodes with other counterparts and their inconsistency in terms of attributes. This paper proposes a self-supervised learning framework that jointly optimizes a multi-view contrastive learning-based module and an attribute reconstruction-based module to more accurately detect anomalies on attributed networks. Specifically, two contrastive learning views are firstly established, which allow the model to better encode rich local and global information related to the abnormality. Motivated by the attribute consistency principle between neighboring nodes, a masked autoencoder-based reconstruction module is also introduced to identify the nodes which have large reconstruction errors, then are regarded as anomalies. Finally, the two complementary modules are integrated for more accurately detecting the anomalous nodes. Extensive experiments conducted on five benchmark datasets show our model outperforms current state-of-the-art models.