Graphlet kernel framework Files

Graphlet Kernels Framework version 1.0 

Jose Lugo-Martinez, jlugomar@indiana.edu
Department of Computer Science
School of Informatics and Computing
Indiana University, Bloomington, IN, USA

This is version 1.0 of the graphlet kernels 
software for vertex classification. This 
version provides a framework for users to 
run a variety of graph-based kernel methods
on (sparse) vertex-labeled undirected and 
directed graphs. The 'graphlet_kernels_v1.0'
folder contains a framework for undirected 
graphs whereas the 'digraphlet_kernels_v1.0' 
folder contains a framework for directed
graphs. Both frameworks support the following 
kernel methods: cumulative random walk, 
standard random walk, standard graphlet kernel, 
edit distance graphlet kernel, label
substitutions graphlet kernel and edge 
indels graphlet kernel. Please refer to the 
correspondiong subfolder on details about how 
to use the framework.

Please direct all comments and bug reports
of this version to jlugomar@indiana.edu

A description of each method and discussion 
of parameters can be found in the paper. 

If you use this framework, please cite our paper:

Lugo-Martinez J. and Radivojac P. "Generalized
Graphlet Kernels for Probabilistic Inference 
in Sparse Graphs", Network Science, 2014.