In this paper, we present CR-Graph (community reinforcement on graphs), a novel method that helps existing algorithms to perform more-accurate community detection (CD). Toward this end, CR-Graph strengthens the community structure of a given original graph by adding non-existent predicted intra-community edges and deleting existing predicted inter-community edges. To design CR-Graph, we propose the following two strategies: (1) predicting intra-community and inter-community edges (i.e., the type of edges) and (2) determining the amount of edges to be added/deleted. To show the effectiveness of CR-Graph, we conduct extensive experiments with various CD algorithms on 7 synthetic and 4 real-world graphs. The results demonstrate that CR-Graph improves the accuracy of all underlying CD algorithms universally and consistently.
|Title of host publication||CIKM 2020 - Proceedings of the 29th ACM International Conference on Information and Knowledge Management|
|Publisher||Association for Computing Machinery|
|Number of pages||4|
|Publication status||Published - 2020 Oct 19|
|Event||29th ACM International Conference on Information and Knowledge Management, CIKM 2020 - Virtual, Online, Ireland|
Duration: 2020 Oct 19 → 2020 Oct 23
|Name||International Conference on Information and Knowledge Management, Proceedings|
|Conference||29th ACM International Conference on Information and Knowledge Management, CIKM 2020|
|Period||20/10/19 → 20/10/23|
Bibliographical noteFunding Information:
This research was supported by (1) the National Research Foundation of Korea grant funded by the Korea government (NRF-2020R1A2B5B03001960), (2) the National Research Foundation of Korea grant funded by the Korea government (2018R1A5A7059549), and (3) the Next-Generation Information Computing Development Program through the National Research Foundation of Korea funded by the Ministry of Science, ICT (NRF-2017M3C4A7069440).
All Science Journal Classification (ASJC) codes
- Business, Management and Accounting(all)
- Decision Sciences(all)