UCoDe: unified community detection with graph convolutional networks

Atefeh Moradan*, Andrew Draganov, Davide Mottin, Ira Assent

*Corresponding author for this work

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Abstract

Community detection finds homogeneous groups of nodes in a graph. Existing approaches either partition the graph into disjoint, non-overlapping, communities, or determine only overlapping communities. To date, no method supports both detections of overlapping and non-overlapping communities. We propose UCoDe, a unified method for community detection in attributed graphs that detects both overlapping and non-overlapping communities by means of a novel contrastive loss that captures node similarity on a macro-scale. Our thorough experimental assessment on real data shows that, regardless of the data distribution, our method is either the top performer or among the top performers in both overlapping and non-overlapping detection without burdensome hyper-parameter tuning.

Original languageEnglish
JournalMachine Learning
Volume112
Issue12
Pages (from-to)5057-5080
Number of pages24
ISSN0885-6125
DOIs
Publication statusPublished - Dec 2023

Keywords

  • Community detection
  • Graph neural networks
  • Modularity
  • Non-overlapping
  • Overlapping

Fingerprint

Dive into the research topics of 'UCoDe: unified community detection with graph convolutional networks'. Together they form a unique fingerprint.

Cite this