Paper Info
Title
Atrributed Graph Embedding Based on Multiobjective Evolutionary Algorithm for Overlapping Community Detection.
Abstract
Graph embedding methods aim to represent nodes in the network into a low-dimensional and continuous vector space while preserving the topological structure and varieties of relational information maximally. Nowadays the structural connections of networks and the attribute information about each node are more easily available than before. As a result, many community detection algorithms for attributed networks have been proposed. However, the majority of these methods cannot deal with the overlapping community detection problem, which is one of the most significant issues in the real-world complex network study. In addition, it is quite challenging to make full use of both structural and attribute information instead of only focusing on one part. To this end, in this paper we innovatively combine the graph embedding with multiobjective evolutionary algorithms (MOEAs) for overlapping community detection problems in attributed networks. As far as I am concerned, MOEA is first used to integrate with graph embedding methods for overlapping community detection. We term our method as MOEA-GE OV , which can automatically determine the number of communities without any prior knowledge and consider topological structure and vertex properties synchronously. In MOEA-GE OV , two objective functions concerning community structure and attribute similarity are carefully designed. Moreover, a heuristic initialization method is proposed to get a relatively good initial population. Then a novel encoding and decoding strategy is designed to efficiently represent the overlapping communities and corresponding embedded representation. In the experiments, the performance of MOEA-GE OV is validated on both single and multiple attribute real-world networks. The experimental results of community detection tasks demonstrate our method can effectively obtain overlapping community structures with practical significance.
Year
DOI
Venue
2020
10.1109/CEC48606.2020.9185758
CEC
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
2
Name
Order
Citations
PageRank
Xiangyi Teng151.75
Jing Liu21043115.54