Graph Autoencoder with Community Neighborhood Network

Ahmet Tüzen*, Yusuf Yaslan

*Corresponding author for this work

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

1 Citation (Scopus)

Abstract

Neighborhood information can be extracted from graph data structure. The neighborhood is valuable because similar objects tend to be connected. Graph neural networks (GNN) represent the neighborhood in layers depending on their proximity. Graph autoencoders (GAE) learn the lower dimensional representation of graph and reconstruct it afterward. The performance of the GAE might be enhanced with the behavior of GNNs. However, utilizing the neighborhood information is challenging. Far neighbors are capable of building redundantly complex networks due to their decreasing similarity. Yet, less neighborhood models are closer to GAE. Restricting the neighborhood within the same community enriches the GNN. In this work, we propose a new unsupervised model that combines GNN and GAE to improve the representation learning of graphs. We examine the outcomes of the model under different neighborhood configurations and hyperparameters. We also prove that the model is applicable to varying sizes and types of graphs within different categories on both synthetic and published datasets. The outcome of the community neighborhood network is resistant to overfitting with fewer learnable parameters.

Original languageEnglish
Title of host publicationIntelligent Systems and Pattern Recognition - 3rd International Conference, ISPR 2023, Revised Selected Papers
EditorsAkram Bennour, Ahmed Bouridane, Lotfi Chaari
PublisherSpringer Science and Business Media Deutschland GmbH
Pages247-261
Number of pages15
ISBN (Print)9783031463372
DOIs
Publication statusPublished - 2024
Event3rd International Conference on Intelligent Systems and Pattern Recognition, ISPR 2023 - Hammamet, Tunisia
Duration: 11 May 202313 May 2023

Publication series

NameCommunications in Computer and Information Science
Volume1941 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference3rd International Conference on Intelligent Systems and Pattern Recognition, ISPR 2023
Country/TerritoryTunisia
CityHammamet
Period11/05/2313/05/23

Bibliographical note

Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

  • graph autoencoder
  • graph neural network
  • graph representation learning
  • neighborhood network

Fingerprint

Dive into the research topics of 'Graph Autoencoder with Community Neighborhood Network'. Together they form a unique fingerprint.

Cite this