Gaussian embedding of large-scale attributed graphs

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

2 Citations (Scopus)


Graph embedding methods transform high-dimensional and complex graph contents into low-dimensional representations. They are useful for a wide range of graph analysis tasks including link prediction, node classification, recommendation and visualization. Most existing approaches represent graph nodes as point vectors in a low-dimensional embedding space, ignoring the uncertainty present in the real-world graphs. Furthermore, many real-world graphs are large-scale and rich in content (e.g. node attributes). In this work, we propose GLACE, a novel, scalable graph embedding method that preserves both graph structure and node attributes effectively and efficiently in an end-to-end manner. GLACE effectively models uncertainty through Gaussian embeddings, and supports inductive inference of new nodes based on their attributes. In our comprehensive experiments, we evaluate GLACE on real-world graphs, and the results demonstrate that GLACE significantly outperforms state-of-the-art embedding methods on multiple graph analysis tasks.

Original languageEnglish
Title of host publicationDatabases Theory and Applications
Subtitle of host publication31st Australasian Database Conference, ADC 2020 Melbourne, VIC, Australia, February 3–7, 2020 Proceedings
EditorsRenata Borovica-Gajic, Jianzhong Qi, Weiqing Wang
Place of PublicationCham Switzerland
Number of pages13
ISBN (Electronic)9783030394691
ISBN (Print)9783030394684
Publication statusPublished - 2020
EventAustralasian Database Conference 2020 - Melbourne, Australia
Duration: 3 Feb 20207 Feb 2020
Conference number: 31st (Proceedings)

Publication series

NameLecture Notes in Computer Science
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349


ConferenceAustralasian Database Conference 2020
Abbreviated titleADC 2020
Internet address


  • Graph embedding
  • Link prediction
  • Node classification

Cite this