Affiliations 

  • 1 LIM Laboratory, Faculty of Sciences and Applied Sciences, University of Bouira, Bouira, Algeria
  • 2 Electrical Engineering Department, Faculty of Sciences and Applied Sciences, University of Bouira, Bouira, Algeria
  • 3 Electronics & Communications Engineering Department, Faculty of Electrical and Electronics Engineering, Istanbul Technical University (ITU), Istanbul, Turkey
  • 4 College of Computer Science & Engineering, University of Ha'il, Ha'il, Saudi Arabia
  • 5 Center for Artificial Intelligence and Robotics (CAIRO), Malaysia-Japan International Institute of Technology, Universiti Teknologi Malaysia, Kuala Lumpur, Malaysia
  • 6 Department of Computer Engineering and Information, College of Engineering in Wadi Alddawasir, Prince Sattam bin Abdulaziz University, Al-Kharj, Saudi Arabia
PeerJ Comput Sci, 2024;10:e2489.
PMID: 39650372 DOI: 10.7717/peerj-cs.2489

Abstract

In this paper, the graph segmentation (GSeg) method has been proposed. This solution is a novel graph neural network framework for network embedding that leverages the inherent characteristics of nodes and the underlying local network topology. The key innovation of GSeg lies in its encoder-decoder architecture, which is specifically designed to preserve the network's structural properties. The key contributions of GSeg are: (1) a novel graph neural network architecture that effectively captures local and global network structures, and (2) a robust node representation learning approach that achieves superior performance in various network analysis tasks. The methodology employed in our study involves the utilization of a graph neural network framework for the acquisition of node representations. The design leverages the inherent characteristics of nodes and the underlying local network topology. To enhance the architectural framework of encoder- decoder networks, the GSeg model is specifically devised to exhibit a structural resemblance to the SegNet model. The obtained empirical results on multiple benchmark datasets demonstrate that the GSeg outperforms existing state-of-the-art methods in terms of network structure preservation and prediction accuracy for downstream tasks. The proposed technique has potential utility across a range of practical applications in the real world.

* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.