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

Graph anomaly detection (GAD) has gained increasing attention in recent yearsdue to its critical application in a wide range of domains, such as socialnetworks, financial risk management, and traffic analysis. Existing GAD methodscan be categorized into node and edge anomaly detection models based on thetype of graph objects being detected. However, these methods typically treatnode and edge anomalies as separate tasks, overlooking their associations andfrequent co-occurrences in real-world graphs. As a result, they fail toleverage the complementary information provided by node and edge anomalies formutual detection. Additionally, state-of-the-art GAD methods, such as CoLA andSL-GAD, heavily rely on negative pair sampling in contrastive learning, whichincurs high computational costs, hindering their scalability to large graphs.To address these limitations, we propose a novel unified graph anomalydetection framework based on bootstrapped self-supervised learning (namedBOURNE). We extract a subgraph (graph view) centered on each target node asnode context and transform it into a dual hypergraph (hypergraph view) as edgecontext. These views are encoded using graph and hypergraph neural networks tocapture the representations of nodes, edges, and their associated contexts. Byswapping the context embeddings between nodes and edges and measuring theagreement in the embedding space, we enable the mutual detection of node andedge anomalies. Furthermore, BOURNE can eliminate the need for negativesampling, thereby enhancing its efficiency in handling large graphs. Extensiveexperiments conducted on six benchmark datasets demonstrate the superioreffectiveness and efficiency of BOURNE in detecting both node and edgeanomalies.

BOURNE: Bootstrapped Self-supervised Learning Framework for Unified Graph Anomaly Detection