GloDyNE: global topology preserving dynamic network embedding (extended abstract)

Chengbin Hou, Han Zhang, Shan He, Ke Tang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Dynamic Network Embedding (DNE) is attracting much attention due to the time-evolving nature of many real-world networks. The main objective of DNE is to efficiently update node embeddings while preserving network topology at each timestep. The idea of most existing DNE methods is to capture the topological changes at or around the most affected nodes (instead of all nodes) and accordingly update node embeddings. Unfortunately, this kind of approximation, although can improve efficiency, cannot effectively preserve the global topology of a dynamic network at each timestep, due to not considering the inactive sub-networks that receive accumulated topological changes propagated via the high-order proximity. To address this issue, we propose a new DNE method for better global topology preservation. Extensive experiments demonstrate the effectiveness and efficiency of the proposed method.

Original languageEnglish
Title of host publication2022 IEEE 38th International Conference on Data Engineering (ICDE)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages2
ISBN (Electronic)9781665408837
ISBN (Print)9781665408844
Publication statusPublished - 2 Aug 2022
Event38th IEEE International Conference on Data Engineering, ICDE 2022 - Virtual, Online, Malaysia
Duration: 9 May 202212 May 2022

Publication series

NameData engineering
ISSN (Print)1084-4627
ISSN (Electronic)2375-026X


Conference38th IEEE International Conference on Data Engineering, ICDE 2022
CityVirtual, Online

Bibliographical note

Publisher Copyright:
© 2022 IEEE.


  • Dynamic Network Embedding
  • Global Topology

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Information Systems


Dive into the research topics of 'GloDyNE: global topology preserving dynamic network embedding (extended abstract)'. Together they form a unique fingerprint.

Cite this