clusters nodes by regularized spectral clustering
community detection by regularized spectral clustering
reg.SP(A, K, tau = 1, lap = FALSE)
A |
adjacency matrix |
K |
number of communities |
tau |
reguarlization parameter. Default value is one. Typically set between 0 and 1. If tau=0, no regularization is applied. |
lap |
indicator. If TRUE, the Laplacian matrix for clustering. If FALSE, the adjacency matrix will be used. |
The regularlization is done by adding a small constant to each element of the adjacency matrix. It is shown by such perturbation helps concentration in sparse networks. It is shown to give consistent clustering under SBM.
a list of
cluster |
cluster labels |
loss |
the loss of Kmeans algorithm |
Tianxi Li, Elizaveta Levina, Ji Zhu
Maintainer: Tianxi Li <tianxili@umich.edu>
K. Rohe, S. Chatterjee, and B. Yu. Spectral clustering and the high-dimensional stochastic blockmodel. The Annals of Statistics, pages 1878-1915, 2011.
A. A. Amini, A. Chen, P. J. Bickel, and E. Levina. Pseudo-likelihood methods for community detection in large sparse networks. The Annals of Statistics, 41(4):2097-2122, 2013.
J. Lei and A. Rinaldo. Consistency of spectral clustering in stochastic block models. The Annals of Statistics, 43(1):215-237, 2014.
C. M. Le, E. Levina, and R. Vershynin. Concentration and regularization of random graphs. Random Structures & Algorithms, 2017.
dt <- BlockModel.Gen(30,300,K=3,beta=0.2,rho=0) A <- dt$A sc <- reg.SP(A,K=3,lap=TRUE) NMI(sc$cluster,dt$g)
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.