iNet: visual analysis of irregular transition in multivariate dynamic networks

Dongming Han, Jiacheng Pan, Rusheng Pan, Dawei Zhou, Nan Cao, Jingrui He, Mingliang Xu, Wei Chen

Research output: Contribution to journalArticlepeer-review


Multivariate dynamic networks indicate networks whose topology structure and vertex attributes are evolving along time. They are common in multimedia applications. Anomaly detection is one of the essential tasks in analyzing these networks though it is not well addressed. In this paper, we combine a rare category detection method and visualization techniques to help users to identify and analyze anomalies in multivariate dynamic networks. We conclude features of rare categories and two types of anomalies of rare categories. Then we present a novel rare category detection method, called DIRAD, to detect rare category candidates with anomalies. We develop a prototype system called iNet, which integrates two major visualization components, including a glyph-based rare category identifier, which helps users to identify rare categories among detected substructures, a major view, which assists users to analyze and interpret the anomalies of rare categories in network topology and vertex attributes. Evaluations, including an algorithm performance evaluation, a case study, and a user study, are conducted to test the effectiveness of proposed methods.

Original languageEnglish (US)
Article number162701
JournalFrontiers of Computer Science
Issue number2
StatePublished - Apr 2022
Externally publishedYes


  • anomaly detection
  • multivariate dynamic networks
  • rare categories
  • visual analysis

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science


Dive into the research topics of 'iNet: visual analysis of irregular transition in multivariate dynamic networks'. Together they form a unique fingerprint.

Cite this