Community Detection Using Deep Learning: Combining Variational Graph Autoencoders with Leiden and K-Truss Techniques

Authors

Jyotika Hariom Patil, San Jose State University
Petros Potikas, National Technical University of Athens (NTUA)
William B. Andreopoulos, San Jose State UniversityFollow
Katerina Potika, San Jose State UniversityFollow

Publication Date

9-1-2024

Document Type

Article

Publication Title

Information (Switzerland)

Volume

15

Issue

9

DOI

10.3390/info15090568

Abstract

Deep learning struggles with unsupervised tasks like community detection in networks. This work proposes the Enhanced Community Detection with Structural Information VGAE (VGAE-ECF) method, a method that enhances variational graph autoencoders (VGAEs) for community detection in large networks. It incorporates community structure information and edge weights alongside traditional network data. This combined input leads to improved latent representations for community identification via K-means clustering. We perform experiments and show that our method works better than previous approaches of community-aware VGAEs.

Keywords

community detection, deep learning, K-truss, Leiden algorithm, variational graph autoencoders

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.

Department

Computer Science

Recommended Citation

Jyotika Hariom Patil, Petros Potikas, William B. Andreopoulos, and Katerina Potika. "Community Detection Using Deep Learning: Combining Variational Graph Autoencoders with Leiden and K-Truss Techniques" Information (Switzerland) (2024). https://doi.org/10.3390/info15090568