Hypergraph network embedding for community detection

Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the ori...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing 2024, Vol.80 (10), p.14180-14202
Main Authors: Xiang, Nan, You, Mingwei, Wang, Qilin, Tian, Bingdi
Format: Article
Language:English
Subjects:
Algorithms
Clustering
Compilers
Computer Science
Embedding
Graph theory
Graphs
Interpreters
Nodes
Processor Architectures
Programming Languages
Representations
Sparsity
Topology
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the original graph structure will suffer from sparsity problems, and will also result in suboptimal node clustering performance. In this paper, we propose a hypergraph network embedding (HGNE) for community detection to solve the above problems. Firstly, we construct potential connections based on the shared feature information of the nodes. By fusing the original topology with feature-based potential connections, both the explicit and implicit relationships are encoded into the node representations, thus alleviating the sparsity problem. Secondly, for integrating the higher-order relationship, we adopt hypergraph convolution to encode the higher-order correlations. To constrain the quality of the node embedding, the spectral hypergraph embedding loss is utilized. Furthermore, we design a dual-contrast mechanism, which draws similar nodes closer by comparing the representations of different views. This mechanism can efficiently prevent multi-node classes from distorting less-node classes. Finally, the dual-contrast mechanism is jointly optimized with self-training clustering to obtain more robust node representations, thus improving the clustering results. Extensive experiments on five datasets indicate the superiority and effectiveness of HGNE.
ISSN:0920-8542
1573-0484
DOI:10.1007/s11227-024-06003-1