spectral.clustering


input matrix -- adjacency matrix of an observed graph based on the non-isolated nodes, of dimension <code>n.noniso</code> x <code>n.noniso</code>, where <code>n.noniso</code> is the number of the non-isolated nodes.



a logic variable indicating whether normalised Laplacian matrix is used in community detection.


normalised


a logical variable indicating whether the RoE is used.


score


input integer -- the pre-specified number of communities, with the default value 2.



Use spectral clustering and its variant for community detection in a network.


Efficient procedures for community detection in network studies, especially for sparse networks with not very obvious community structure. The algorithms impose penalties on the differences of the coordinates which represent the community labels of the nodes.

spectral.clustering: Spectral clustering and its variant.

Description

Usage

Arguments

Value