GEMSEC: Graph Embedding with Self Clustering

Benedek Rózemberczki, Ryan Davies, Rik Sarkar, Charles Sutton

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

Abstract

Modern graph embedding procedures can efficiently process graphs with millions of nodes. In this paper, we propose GEMSEC – a graph embedding algorithm which learns a clustering of the nodes simultaneously with computing their embedding. GEMSEC is a general extension of earlier work in the domain of sequence-based graph embedding. GEMSEC places nodes in an abstract feature space where the vertex features minimize the negative log-likelihood of preserving sampled vertex neighborhoods, and it incorporates known social network properties through a machine learning regularization.

We present two new social network datasets and show that by simultaneously considering the embedding and clustering problems with respect to social properties, GEMSEC extracts high-quality clusters competitive with or superior to other community detection algorithms. In experiments, the method is found to be computationally efficient and robust to the choice of hyperparameters.
Original languageEnglish
Title of host publicationASONAM '19: Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining
Editors Francesca Spezzano, Wei Chen, Xiaokui Xiao
PublisherAssociation for Computing Machinery (ACM)
Pages65-72
Number of pages8
ISBN (Print)9781450368681
DOIs
Publication statusPublished - 27 Aug 2019
EventIEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) 2019 - Marriot Downtown Hotel, Vancouver, Canada
Duration: 27 Aug 201930 Aug 2019
Conference number: 11
http://asonam.cpsc.ucalgary.ca/2019/

Conference

ConferenceIEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) 2019
Abbreviated titleASONAM 2019
CountryCanada
CityVancouver
Period27/08/1930/08/19
Internet address

Keywords

  • community detection
  • clustering
  • node embedding
  • network embedding
  • feature extraction

Fingerprint

Dive into the research topics of 'GEMSEC: Graph Embedding with Self Clustering'. Together they form a unique fingerprint.

Cite this