Recurrent Graph Neural Network Algorithm for Unsupervised Network Community Detection

2021-03-03 · Stanislav Sobolevsky

Network community detection often relies on optimizing partition quality functions, like modularity. This optimization appears to be a complex problem traditionally relying on discrete heuristics. And although the problem could be reformulated as continuous optimization, direct application of the standard optimization methods has limited efficiency in overcoming the numerous local extrema. However, the rise of deep learning and its applications to graphs offers new opportunities. And while graph neural networks have been used for supervised and unsupervised learning on networks, their application to modularity optimization has not been explored yet. This paper proposes a new variant of the recurrent graph neural network algorithm for unsupervised network community detection through modularity optimization. The new algorithm's performance is compared against a popular and fast Louvain method and a more efficient but slower Combo algorithm recently proposed by the author. The approach also serves as a proof-of-concept for the broader application of recurrent graph neural networks to unsupervised network optimization.

📄 PDF Abstract BibTeX arXiv:2103.02520

Code (1)

alexander-belyi/gnns

Tasks

Community Detection Graph Neural Network

Methods 이 논문이 사용한 방법론

Graph Neural Network 설명 없음

Unsupervised Constrained Community Detection via Self-Expressive Graph Neural Network

2020-11-28 · Sambaran Bandyopadhyay, Vishal Peter

Graph neural networks (GNNs) are able to achieve promising performance on multiple graph downstream tasks such as node classification and link prediction. Comparatively lesser work has been done to design GNNs which can …

Clustering Community Detection Graph Neural Network Link Prediction+1

Curvature-based Clustering on Graphs

2023-07-19 · Yu Tian, Zachary Lubberts, Melanie Weber

Unsupervised node clustering (or community detection) is a classical graph learning task. In this paper, we study algorithms, which exploit the geometry of the graph to identify densely connected substructures, which for…

Clustering Community Detection Graph Learning Node Clustering

Community-Aware Efficient Graph Contrastive Learning via Personalized Self-Training

2023-11-18 · Yuecheng Li, YanMing Hu, Lele Fu, Chuan Chen 외

In recent years, graph contrastive learning (GCL) has emerged as one of the optimal solutions for various supervised tasks at the node level. However, for unsupervised and structure-related tasks such as community detect…

Community Detection Contrastive Learning Graph Clustering

The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks

2023-10-02 · Christopher Blöcker, Chester Tan, Ingo Scholtes

Community detection is an essential tool for unsupervised data exploration and revealing the organisational structure of networked systems. With a long history in network science, community detection typically relies on …

Clustering Community Detection Graph Clustering Graph Neural Network+1

Non-Dissipative Graph Propagation for Non-Local Community Detection

2025-08-15 · William Leeney, Alessio Gravina, Davide Bacciu arxiv

Community detection in graphs aims to cluster nodes into meaningful groups, a task particularly challenging in heterophilic graphs, where nodes sharing similarities and membership to the same community are typically dist…

Graph Neural Network Community Detection