Abstract
We propose a quantitative function for community partition—i.e., modularity density or value. We demonstrate that this quantitative function is superior to the widely used modularity and also prove its equivalence with the objective function of the kernel means. Both theoretical and numerical results show that optimizing the new criterion not only can resolve detailed modules that existing approaches cannot achieve, but also can correctly identify the number of communities.
- Received 6 October 2007
DOI:https://doi.org/10.1103/PhysRevE.77.036109
©2008 American Physical Society