Skip to content
forked from glsjsu/rprr2018

Matlab code for a scalable spectral clustering algorithm with cosine similarity

License

Notifications You must be signed in to change notification settings

ChangLu92/rprr2018

 
 

Repository files navigation

Scalable Spectral Clustering with Cosine Similarity (ssc-cosine)

This is a brief documentation for the Matlab implementation of the algorithm and experiments in the following paper "Scalable Spectral Clustering with Cosine Similarity", G. Chen, ICPR 2018, Beijing, China

To reproduce all the results of the paper, just do the following:

  • Download the ssc-cosine.zip file and uncompress it
  • Download all the .mat files and store them in a subfolder called Data. Run script_merge_data.m from the parent folder to merge portions of some data sets (20news and mnist) that are stored separately.
  • Run script_all.m from the parent folder in MATLAB.

Structure of the package

  • Main function: ssc-cosine.m

  • Scripts used to reproduce the individual results reported in the ICPR18 paper:

    • script_20news_processing: This script processes the raw 20newsgroups data (Matlab bydate version) downloadable from http://qwone.com/~jason/20Newsgroups/ (executing this script is optional as the processed data has been provided).
    • script_20news_results.m: Table I
    • script_20news_insights.m: Figure 2
    • script_20news_alpha.m: Figure 3
    • script_tdt2_top30_results.m: Figure 4
    • script_digits_results.m: Table II
  • Scripts used to reproduce the results reported in the short paper:

    • script_20news_alpha_scalable3.m: Figure 1
    • script_tdt2_top30_DMt.m: Figure 2

Required external functions:

  • The kmeans.m function, available through the Statistics and Machine Learning Toolbox, is needed by the main function ssc-cosine.m. If that toolbox is not available in the computer, then one may use instead a substitute kmeans implementation, such as the litekmeans.m function available at http://www.cad.zju.edu.cn/home/dengcai/Data/Clustering.html.

  • The bestMap.m function, available also on the above webpage, is needed by the scripts for finding the best match between the ground-truth labels and the group labels obtained by the function ssc-cosine.m, in order to compute the clustering accuracy.

For your convenience, the litekmeans.m and bestMap.m functions have been included in this repository.

About

Matlab code for a scalable spectral clustering algorithm with cosine similarity

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published