DMC {ORKM}

Deep matrix clustering algorithm for multi-view data

Description

This algorithm decomposes the multi-view data matrix into representative subspaces layer by layer, and generates a cluster at each layer. To enhance the diversity between the generated clusters, new redundant quantifiers arising from the proximity between samples in these subspaces are minimised. An iterative optimisation process is further introduced to simultaneously seek multiple clusters with quality and diversity.

Usage

DMC(X, K, V, r, lamda, truere, max.iter, method = 0)

Arguments

X

data matrix

K

number of cluster

V

number of view

r

first banlance parameter

lamda

second balance parameter

truere

true cluster result

max.iter

max iter

method

caculate the index of NMI

Value

NMI,Alpha1,center,result

Author(s)

Miao Yu

Examples

 library(MASS)   
 V=2;lamda=0.5;K=3;r=0.5;max.iter=10;n1=n2=n3=70
 X1<-rnorm(n1,20,2);X2<-rnorm(n2,25,1.5);X3<-rnorm(n3,30,2) 
 Xv<-c(X1,X2,X3)
 data<-matrix(Xv,n1+n2+n3,2)
 data[1:70,2]<-1;data[71:140,2]<-2;data[141:210,2]<-3
 truere=data[,2]
 X<-matrix(data[,1],n1+n2+n3,1) 
 lamda1<-0.2;lamda2<-0.8
 lamda0<-matrix(c(lamda1,lamda2),nrow=1,ncol=2)
 sol.svd <- svd(lamda0)
 U1<-sol.svd$u
 D1<-sol.svd$d
 V1<-sol.svd$v
 C1<-t(U1)%*%t(X)
 Y1<-C1/D1
 view<-V1%*%Y1
 view1<-matrix(view[1,])
 view2<-matrix(view[2,])
 X1<-matrix(view1,n1+n2+n3,1)
 X2<-matrix(view2,n1+n2+n3,1)
 DMC(X=X1,K=K,V=V,lamda=lamda,r=r,max.iter=max.iter,truere=truere,method=0)