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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Graph anomaly detection (GAD) has attracted increasing attention in machinelearning and data mining. Recent works have mainly focused on how to capturericher information to improve the quality of node embeddings for GAD. Despitetheir significant advances in detection performance, there is still a relativedearth of research on the properties of the task. GAD aims to discern theanomalies that deviate from most nodes. However, the model is prone to learnthe pattern of normal samples which make up the majority of samples. Meanwhile,anomalies can be easily detected when their behaviors differ from normality.Therefore, the performance can be further improved by enhancing the ability tolearn the normal pattern. To this end, we propose a normality learning-basedGAD framework via multi-scale contrastive learning networks (NLGAD forabbreviation). Specifically, we first initialize the model with the contrastivenetworks on different scales. To provide sufficient and reliable normal nodesfor normality learning, we design an effective hybrid strategy for normalityselection. Finally, the model is refined with the only input of reliable normalnodes and learns a more accurate estimate of normality so that anomalous nodescan be more easily distinguished. Eventually, extensive experiments on sixbenchmark graph datasets demonstrate the effectiveness of our normalitylearning-based scheme on GAD. Notably, the proposed algorithm improves thedetection performance (up to 5.89% AUC gain) compared with the state-of-the-artmethods. The source code is released at https://github.com/FelixDJC/NLGAD.

Normality Learning-based Graph Anomaly Detection via Multi-Scale Contrastive Learning