Modularity-driven kernel k-means for community detection
(2017) , 15 pages
Files
2017-21FelixSommer.pdf
Open Access - Adobe PDF
- 776.78 KB
Details
- Authors
- Abstract
- Nowadays, k-means is probably the most well-known and most popular clustering method in existence. This work evaluates if a new, autonomous, kernel k-means approach for graph node clustering coupled with the modularity criterion can rival the well-established Lou- vain method. We test the algorithm on social network datasets of various sizes and types. The new method estimates the optimal kernel or distance parameters as well as the natural number of clusters in the dataset. Results indicate that this new black-box algorithm manages to perform on par with the Louvain method given the same input
- Affiliations
Citations
Sommer, F., Fouss, F., & Saerens, M. (2017). Modularity-driven kernel k-means for community detection (Louvain Research Institute in Management and Organizations Working Paper Series 2017/21). https://hdl.handle.net/2078.5/173411