Spectral clustering (fast)

Perform spectral clustering (with regularization) to estimate communities

spec_clust(
  A,
  K,
  type = "lap",
  tau = 0.25,
  nstart = 20,
  niter = 10,
  ignore_first_col = F
)

Arguments

A

Adjacency matrix (n x n)

K

Number of communities

type

("lap" | "adj" | "adj2") Whether to use Laplacian or adjacency-based spectral clustering

tau

Regularization parameter for the Laplacian

nstart

argument from function 'kmeans'

niter

argument from function 'kmeans'

ignore_first_col

whether to ignore the first eigen vector when doing spectral clustering

Value

A label vector of size n x 1 with elements in 1,2,...,K