A Systematic Review of Graph Neural Network for Node Clustering in Homogeneous Attributed Networks
Open Access
- 19 December 2025
- journal article
- review article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 215265-215285
Abstract
The objective of node clustering is to identify distinct groups of vertices in a graph, ensuring that similar nodes are grouped together while dissimilar ones remain apart. Building on the success of graph neural networks (GNNs) in tasks such as node classification and link prediction, several clustering strategies have been developed. Although these methods are highly effective, many share similar strengths and weaknesses, which are often difficult to discern in the absence of a clear taxonomy. Previous studies have attempted to categorize node clustering algorithms; however, most are not restricted to GNN-based methods and instead encompass a wide variety of graph learning techniques. Furthermore, despite significant progress in community detection, valuable insights from this area remain underexplored in the context of GNN-based clustering. To bridge this gap and provide a structured overview of the field, we conducted a Systematic Literature Review (SLR) on node clustering in homogeneous networks using GNNs. A total of 84 articles were reviewed based on 20 inclusion and exclusion criteria. From this analysis, we propose a comprehensive taxonomy that integrates both deep clustering and node embedding models. The findings reveal key research gaps, including the absence of transformer-based models, the high computational cost of some approaches, and dataset bias arising from the over-reliance on widely used benchmarks. The proposed taxonomy offers a clearer framework for understanding existing methodologies and guiding future research directions in GNN-based node clustering.Keywords
Funding Information
- Coordination for the Improvement of Higher Education Personnel (CAPES), through a Ph.D. Scholarship (001)
- São Paulo Research Foundation (2022/03090-0)
- National Council for Scientific and Technological Development (420025/2023-5)
- National Council for Scientific and Technological Development (309575/2021-4)
This publication has 137 references indexed in Scilit:
- Deep Learning-Based Attribute Graph Clustering: An Overview2024
- Hierarchical Graph Neural Network for Patient Treatment Preference Prediction with External Knowledge2023
- Identifying Fraud Rings Using Domain Aware Weighted Community Detection2022
- Using Relational Graph Convolutional Networks to Assign Fashion Communities to Users2022
- End-to-end variational graph clustering with local structural preservationNeural Computing and Applications, 2021
- On Generalization of Graph Autoencoders with Adversarial Training2021
- Simple and Effective Graph Autoencoders with One-Hop Linear Models2021
- DANCer: Dynamic Attributed Network with Community Structure Generator2016
- Systematic Reviews in the Social Sciences2006
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982