Localized Multiple Kernel k-Means Clustering
Switch branches/tags
Nothing to show
Clone or download
Pull request Compare This branch is 4 commits behind mehmetgonen:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
README
demo_kernel_kmeans.m
demo_localized_multiple_kernel_kmeans.m
demo_multiple_kernel_kmeans.m
kkmeans_train.m
lmkkmeans_train.m
mkkmeans_train.m

README

This package contains Matlab implementations of the clustering algorithms in "Localized Data Fusion for Kernel k-Means Clustering with Application to Cancer Biology", which is appearing in NIPS 2014.

demo_kernel_kmeans.m file shows how to use the kernel k-means clustering algorithm.
demo_multiple_kernel_kmeans.m file shows how to use the multiple kernel k-means clustering algorithm.
demo_localized_multiple_kernel_kmeans.m file shows how to use the localized multiple kernel k-means clustering algorithm.

clustering methods
------------------
* kkmeans_train.m => training procedure for kernel k-means
* mkkmeans_train.m => training procedure for multiple kernel k-means (requries Mosek optimization software)
* lmkkmeans_train.m => training procedure for localized multiple kernel k-means (requries Mosek optimization software)

If you use any of the algorithms implemented in this package, please cite the following paper:

Mehmet Gonen and Adam A. Margolin. Localized Data Fusion for Kernel k-Means Clustering with Application to Cancer Biology. Advances in Neural Information Processing Systems 27 (NIPS 2014), Montreal, Québec, Canada, 2014.