evaluation function

Consistent Estimation of the Number of Communities via Regularized Network Embedding.

The evaluation function for Consistent Estimation of the Number of Communities via Regularized Network Embedding.

evaluation(Z.hat, Z.true, cluster.matrix.hat, cluster.matrix.true,
                  P.true, Theta.true, K.hat=4, K.true=4)

Arguments

• Z.hat: A n * r matrix, the estimated embedding vectors corresponding to n nodes.
• Z.true: A n * r matrix, the true embedding vectors corresponding to n nodes.
• cluster.matrix.hat: A n * n estimated membership matrix, whose (i,j)-element is 1, if nodes i and j are estimated to belong to the same community, and 0, otherwise.
• cluster.matrix.true: A n * n true membership matrix, whose (i,j)-element is 1, if nodes i and j belong to the same community, and 0, otherwise.
• P.true: A n * n true probability matrix.
• Theta.true: A n * n true matrix: Z.true %*% t(Z.true).
• K.hat: The true number of communities.
• K.true: The estimated number of communities.

Returns

A vector including five evaluation index. prop. 1: the estimated and actual number of communities are equal; 0: not equal.

Author(s)

Mingyang Ren.