English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Detecting anomalous edges and nodes in dynamic networks is critical invarious areas, such as social media, computer networks, and so on. Recentapproaches leverage network embedding technique to learn how to generate noderepresentations for normal training samples and detect anomalies deviated fromnormal patterns. However, most existing network embedding approaches learndeterministic node representations, which are sensitive to fluctuations of thetopology and attributes due to the high flexibility and stochasticity ofdynamic networks. In this paper, a stochastic neural network, named byHierarchical Variational Graph Recurrent Autoencoder (H-VGRAE), is proposed todetect anomalies in dynamic networks by the learned robust node representationsin the form of random variables. H-VGRAE is a semi-supervised model to capturenormal patterns in training set by maximizing the likelihood of the adjacencymatrix and node attributes via variational inference. Comparing with existingmethods, H-VGRAE has three main advantages: 1) H-VGRAE learns robust noderepresentations through stochasticity modeling and the extraction ofmulti-scale spatial-temporal features; 2) H-VGRAE can be extended to deepstructure with the increase of the dynamic network scale; 3) the anomalous edgeand node can be located and interpreted from the probabilistic perspective.Extensive experiments on four real-world datasets demonstrate theoutperformance of H-VGRAE on anomaly detection in dynamic networks comparedwith state-of-the-art competitors.

H-VGRAE: A Hierarchical Stochastic Spatial-Temporal Embedding Method for Robust Anomaly Detection in Dynamic Networks