ReadGraph: Relational Evolution Enhanced Anomaly Detection in Dynamic Heterogeneous Graph

Xiaolin Han, Xiurui Hu, Chenhao Ma, Xuequn Shang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Abnormal behavior detection is crucial in many fields, such as social networks, financial transactions, and cybersecurity. However, it poses significant challenges due to the intricate structural evolution of heterogeneous graphs. To address this issue, we propose a novel method called Relational Evolution enhanced Anomaly Detection in dynamic heterogeneous Graph (ReadGraph). ReadGraph focuses on tracing relation-based dynamic structural evolution to comprehensively capture features related to abnormal behaviors (edges) across different types of nodes. We conduct extensive experiments to evaluate ReadGraph against advanced competitors. It demonstrates that ReadGraph is 13.69% more effective than other methods on average.

Original languageEnglish
Title of host publicationWWW Companion 2025 - Companion Proceedings of the ACM Web Conference 2025
PublisherAssociation for Computing Machinery, Inc
Pages1009-1013
Number of pages5
ISBN (Electronic)9798400713316
DOIs
StatePublished - 23 May 2025
Event34th ACM Web Conference, WWW Companion 2025 - Sydney, Australia
Duration: 28 Apr 20252 May 2025

Publication series

NameWWW Companion 2025 - Companion Proceedings of the ACM Web Conference 2025

Conference

Conference34th ACM Web Conference, WWW Companion 2025
Country/TerritoryAustralia
CitySydney
Period28/04/252/05/25

Keywords

  • Anomaly detection
  • Dynamic heterogeneous graph

Fingerprint

Dive into the research topics of 'ReadGraph: Relational Evolution Enhanced Anomaly Detection in Dynamic Heterogeneous Graph'. Together they form a unique fingerprint.

Cite this