Skip to main navigation Skip to search Skip to main content

SPATIO-TEMPORAL ANOMALY DETECTION FOR LARGE-SCALE DYNAMIC ATTRIBUTED NETWORKS

  • Tsinghua University

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

Abstract

Dynamic attributed networks (DANs) provide powerful means of representing complex system, e.g., online social networks, financial networks, transactional networks, and wireless sensor networks. To facilitate situation awareness and critical decision-making, anomaly detection in DANs has become an increasingly active area of research in network sciences. However, most existing methods are only capable of detecting the temporal outliers, neglecting the potential benefits of jointly detecting the spatial outliers across the entire network. To address this issue, this paper presents a novel approach, which is also efficient for large-scale networks. Specifically, we first develop a novel recurrent neural network structure to explore the spatio-temporal correlations of the DANs. Furthermore, prediction residuals are monitored through an exponentially weighted moving average (EWMA) control chart. Experiments on synthetic and real-world datasets depict the properties and benefits of the method compared with existing methods in the literature.

Original languageEnglish
Title of host publicationProceedings of the 31st European Safety and Reliability Conference, ESREL 2021
EditorsBruno Castanier, Marko Cepin, David Bigaud, Christophe Berenguer
PublisherResearch Publishing, Singapore
Pages2932
Number of pages1
ISBN (Print)9789811820168
DOIs
StatePublished - 2021
Externally publishedYes
Event31st European Safety and Reliability Conference, ESREL 2021 - Angers, France
Duration: 19 Sep 202123 Sep 2021

Publication series

NameProceedings of the 31st European Safety and Reliability Conference, ESREL 2021

Conference

Conference31st European Safety and Reliability Conference, ESREL 2021
Country/TerritoryFrance
CityAngers
Period19/09/2123/09/21

Keywords

  • Anomaly detection
  • Dynamic attributed networks
  • Exponentially weighted moving average control chart
  • Large-scale networks
  • Recurrent neural network structure
  • Spatio-temporal correlations

Fingerprint

Dive into the research topics of 'SPATIO-TEMPORAL ANOMALY DETECTION FOR LARGE-SCALE DYNAMIC ATTRIBUTED NETWORKS'. Together they form a unique fingerprint.

Cite this