evclust (version 2.0.3)

pcca: Pairwise Constrained Component Analysis (PCCA)

Description

Using must-link and cannot-link constaints, PCCA (Mignon & Jury, 2012) learns a projection into a low-dimensional space where the distances between pairs of data points respect the desired constraints, exhibiting good generalization properties in presence of high dimensional data.

Usage

pcca(x, d1, ML, CL, options = c(1, 1000, 1e-05, 10), beta = 1)

Value

A list with three attributes:

z

The n*d1 matrix of extracted features.

L

The projection matrix of size d1*d.

D

The Euclidean distance matrix in the projected space

Arguments

x

Data matrix of size n*d

d1

Number of extracted features.

ML

Matrix nbML x 2 of must-link constraints. Each row of ML contains the indices of objects that belong to the same class.

CL

Matrix nbCL x 2 of cannot-link constraints. Each row of CL contains the indices of objects that belong to different classes.

options

Parameters of the optimization algorithm (see harris).

beta

Sharpness parameter in the loss function (default: 1).

Author

Thierry Denoeux.

References

A. Mignon and F. Jurie. PCCA: a new approach for distance learning from sparse pairwise constraints. In 2012 IEEE Conference on Computer Vision and Pattern Recognition, pages 2666-2672, 2012.

See Also

kpcca,harris,create_MLCL

Examples

if (FALSE) {
data(iris)
x<-as.matrix(iris[,1:4])
y<-as.integer(iris[,5])
const<-create_MLCL(y,50)
res.pcca<-pcca(x,1,const$ML,const$CL)
plot(res.pcca$z,col=y,pch=y)
}