Semi-Supervised Community Detection Based on Distance Dynamics

Community detection methods that are based entirely on the topology of the network do not always achieve higher accuracy. This implies that the topological information alone is insufficient to accurately uncover the community structures of networks. Recently, some methods were proposed that used pri...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 6; pp. 37261 - 37271
Main Authors Fan, Lilin, Xu, Shengli, Liu, Dong, Ru, Yan
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 01.01.2018
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Accuracy
Clustering algorithms
Community detection
Computer science
Detection algorithms
distance dynamics
graphs
Heuristic algorithms
Mathematical model
Network topology
Networks
semi-supervised
Topology
Online AccessGet full text

Cover

More Information
Summary:Community detection methods that are based entirely on the topology of the network do not always achieve higher accuracy. This implies that the topological information alone is insufficient to accurately uncover the community structures of networks. Recently, some methods were proposed that used prior information to improve the performance and accuracy of community detection. However, most of these methods have high time consumption and are not suitable for dealing with large-scale networks. In this paper, we propose a fast semi-supervised community detection method called SemiAttractor that integrates the prior information into the distance dynamics model. Experimental results from both artificial and real-world networks show that the proposed method can effectively improve the accuracy of community detection and reduce the time costs.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2018.2838568