Fuzzy Community Detection with Multi-View Correlated Topics

Page view(s)
0
Checked on
Fuzzy Community Detection with Multi-View Correlated Topics
Title:
Fuzzy Community Detection with Multi-View Correlated Topics
Journal Title:
IEEE/WIC/ACM International Conference on Web Intelligence
Publication Date:
11 April 2022
Citation:
Yao, L., & He, T. (2021). Fuzzy Community Detection with Multi-View Correlated Topics. IEEE/WIC/ACM International Conference on Web Intelligence, 307–313. https://doi.org/10.1145/3498851.3498971
Abstract:
In this paper, we present a novel fuzzy framework, dubbed as Fuzzy Multi-View Featured Network Clustering (FMVFNC), for effectively uncovering overlapping communities in social network data. Unlike most previous efforts which utilize only edge structure and single view of vertex features to perform the community discovery task, the proposed FMVFNC is able to take advantage of both edge structure and correlated vertex features which may be collected from multiple views. As the uncovered social communities are described by both network structure and semantically correlated features from diverse modalities, their practical significance can be well revealed. We innovatively design a unified fuzzy objective for FMVFNC to perform the task. We then derive an iterative algorithm for the proposed framework to optimize the formulated objective function. FMVFNC has been tested with a number of well-established datasets and has been compared with a number of state-of-the-art baselines for community detection. The notable results obtained may validate the effectiveness of FMVFNC.
License type:
Publisher Copyright
Funding Info:
There was no specific funding for the research done
Description:
© ACM 2022. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in WI-IAT '21: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, http://dx.doi.org/10.1145/3498851.3498971
ISSN:
78-1-4503-9187-0/21/12
Files uploaded:

File Size Format Action
sample-sigconf.pdf 620.36 KB PDF Open