Community Detection Based on Graph Representation Learning in Evolutionary Networks
Open Access
- 14 May 2021
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 11 (10) , 4497
Abstract
Aiming at analyzing the temporal structures in evolutionary networks, we propose a community detection algorithm based on graph representation learning. The proposed algorithm employs a Laplacian matrix to obtain the node relationship information of the directly connected edges of the network structure at the previous time slice, the deep sparse autoencoder learns to represent the network structure under the current time slice, and the K-means clustering algorithm is used to partition the low-dimensional feature matrix of the network structure under the current time slice into communities. Experiments on three real datasets show that the proposed algorithm outperformed the baselines regarding effectiveness and feasibility.Keywords
Funding Information
- Natural Science Foundation of Liaoning Province (20170540320)
- Doctoral Scientific Research Foundation of Liaoning Province (20170520358)
- Fundamental Research Funds for the Central Universities (N161702001;N172410005-2)
This publication has 30 references indexed in Scilit:
- Structural Deep Network Embedding2016
- LINE2015
- Structure and Evolution of Online Social Networks2010
- Nonlinear Dimensionality Reduction by Locally Linear InlayingIEEE Transactions on Neural Networks, 2009
- Blog Community Discovery and Evolution Based on Mutual Awareness Expansion2007
- An event-based framework for characterizing the evolutionary behavior of interaction graphs2007
- On the Bursty Evolution of BlogspaceWorld Wide Web, 2005
- A Global Geometric Framework for Nonlinear Dimensionality ReductionScience, 2000
- Collective dynamics of ‘small-world’ networksNature, 1998
- Silhouettes: A graphical aid to the interpretation and validation of cluster analysisJournal of Computational and Applied Mathematics, 1987