Autoencoder Model Using Edge Enhancement to Detect Communities in Complex Networks

Community structure is the utmost significant characteristics in complex networks. Numerous algorithms of community detection have been developed so far. Some methods consider only the lower-order framework, i.e. nodes and edges, and neglect the higher-order framework, whereas other recent methods c...

Full description

Saved in:
Bibliographic Details
Published in:Arabian journal for science and engineering (2011) Vol. 48; no. 2; pp. 1303 - 1314
Main Authors: Chaudhary, Laxmi, Singh, Buddha
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2023
Springer Nature B.V
Subjects:
Algorithms
Engineering
Graph theory
Humanities and Social Sciences
Modularity
multidisciplinary
Networks
Redesign
Research Article-Computer Engineering and Computer Science
Science
Deep learning
Community detection
Social networks
Communities
Autoencoder
Complex networks
ISSN:2193-567X, 1319-8025, 2191-4281
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Community structure is the utmost significant characteristics in complex networks. Numerous algorithms of community detection have been developed so far. Some methods consider only the lower-order framework, i.e. nodes and edges, and neglect the higher-order framework, whereas other recent methods capture higher-order framework, i.e. motifs (a small dense subgraph), yet they mainly put emphasis on the connected motif hypergraph. These methods help to encounter only fragmentation issue. Moreover, the other major issue in complex network is to reduce the dimension and extract the significant characteristics. In addition to this, the existing methods have sparsity and computational issues as well. Hence, we have developed an autoencoder model using edge enhancement (AMEE) to tackle these issues and uncover the hidden communities in complex networks. It begins by emphasizing edge enhancement to redesign the network connectivity of input network and creates a rewired graph. Embedding of a rewired network is obtained by applying the Autoencoder model. Finally, a community detection technique is applied to reveal the communities. Hence, the proposed method (AMEE) deals with the above-mentioned issues efficiently. Furthermore, a comprehensive analysis of the proposed method is carried out on eight different real-world network datasets, i.e. Polbooks, Email, Polblogs, Cora, Facebook, Com-Orkut, Com-Amazon and Com-Youtube. The Modularity score, F -score and normalized mutual information are used as evaluation parameters to measure the performance of the proposed method. The higher value of these measures clearly indicates the efficacy and quality of the communities achieved using the proposed approach. It shows a significant improvement in comparison with other existing community detection techniques.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2193-567X
1319-8025
2191-4281
DOI:10.1007/s13369-022-06747-z