Fast Sequence Based Embedding with Diffusion Graphs

Benedek Rózemberczki, Rik Sarkar

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

Abstract / Description of output

A graph embedding is a representation of the vertices of a graph in a low dimensional space, which approximately preserves properties such as distances between nodes. Vertex sequence based embedding procedures use features extracted from linear sequences of vertices to create embeddings using a neural network. In this paper, we propose diusion graphs as a method to rapidly generate vertex sequences for network embedding. Its computational eciency is superior to previous methods due to simpler sequence generation, and it produces more accurate results. In experiments, we found that the performance relative to other methods improves with increasing edge density in the graph. In a community detection task, clustering nodes in the embedding space produces better results compared to other sequence based embedding methods.
Original languageEnglish
Title of host publicationProceedings for International Conference on Complex Networks 2018
Place of PublicationBoston, USA
Number of pages12
ISBN (Electronic)978-3-319-73198-8
ISBN (Print)978-3-319-73197-1
Publication statusPublished - 2018
EventInternational Conference on Complex Networks - Boston, United States
Duration: 5 Mar 20188 Mar 2018

Publication series

NameSpringer Proceedings in Complexity (SPCOM)
PublisherSpringer, Cham
ISSN (Print)2213-8684
ISSN (Electronic)2213-8692


ConferenceInternational Conference on Complex Networks
Abbreviated titleCompleNet 2018
Country/TerritoryUnited States
Internet address


Dive into the research topics of 'Fast Sequence Based Embedding with Diffusion Graphs'. Together they form a unique fingerprint.

Cite this