Deep Anomaly Detection on Attributed Networks.

TL;DR: This paper develops a novel deep model that explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN) and is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data.

Abstract: Attributed networks are ubiquitous and form a critical component of modern information infrastructure, where additional node attributes complement the raw network structure in knowledge discovery. Recently, detecting anomalous nodes on attributed networks has attracted an increasing amount of research attention, with broad applications in various high-impact domains, such as cybersecurity, finance, and healthcare. Most of the existing attempts, however, tackle the problem with shallow learning mechanisms by ego-network or community analysis, or through subspace selection. Undoubtedly, these models cannot fully address the computational challenges on attributed networks. For example, they often suffer from the network sparsity and data nonlinearity issues, and fail to capture the complex interactions between different information modalities, thus negatively impact the performance of anomaly detection. To tackle the aforementioned problems, in this paper, we study the anomaly detection problem on attributed networks by developing a novel deep model. In particular, our proposed deep model: (1) explicitly models the topological structure and nodal attributes seamlessly for node embedding learning with the prevalent graph convolutional network (GCN); and (2) is customized to address the anomaly detection problem by virtue of deep autoencoder that leverages the learned embeddings to reconstruct the original data. The synergy between GCN and autoencoder enables us to spot anomalies by measuring the reconstruction errors of nodes from both the structure and the attribute perspectives. Extensive experiments on real-world attributed network datasets demonstrate the efficacy of our proposed algorithm.