Graph based community detection methods are very effective in explaining the underlying structure of graph but i have not come across any method find optimal number of community similar to clustering methods.
Say, I am trying to identify the communities in an unsupervised manner and for that I am trying to maximize the modularity. Now, I get different number of communities with different nodes even at a single resolution parameter. The question arises which of the communities is the best i.e. is there any statistical criteria which can lead me to find that number?
Moreover, the choice of resolution parameter itself is a question mark.