Research Article
A Community Discovery Algorithm Using Increment of Modularity to Optimize the Label Propagation Process
@INPROCEEDINGS{10.1007/978-3-031-32443-7_17, author={Xinqi Xu and Xiaoyan Zheng}, title={A Community Discovery Algorithm Using Increment of Modularity to Optimize the Label Propagation Process}, proceedings={Mobile Networks and Management. 12th EAI International Conference, MONAMI 2022, Virtual Event, October 29-31, 2022, Proceedings}, proceedings_a={MONAMI}, year={2023}, month={5}, keywords={Community detection Label propagation Modularity Optimization}, doi={10.1007/978-3-031-32443-7_17} }- Xinqi Xu
Xiaoyan Zheng
Year: 2023
A Community Discovery Algorithm Using Increment of Modularity to Optimize the Label Propagation Process
MONAMI
Springer
DOI: 10.1007/978-3-031-32443-7_17
Abstract
Due to the strong randomness of label selection, the label propagation algorithm makes the community results unstable. Especially in asynchronous updates, the final results are quite different due to the different order of selecting listeners. This paper proposes a community discovery algorithm using increment of modularity to optimize the label propagation process. In the process of label propagation, the increment of modularity is introduced to ensure that the increment of modularity is positive in each update. At the same time, the selection of popular nodes in traditional label propagation algorithms is retained. Combining these two methods, each node selection improve the division of the community and reduce the possibility of poor results due to asynchronous updates. The algorithm is verified in real network, and the results show that the algorithm is feasible and effective.
