Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Latest commit e42e261 Dec 3, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
data Finalized experiments Oct 16, 2019
experiments Tests implemented Dec 2, 2019
src New version Dec 2, 2019
supporting_material Updated poster Dec 3, 2019
.gitignore New version Dec 2, 2019 Updated poster Dec 3, 2019

Wasserstein Weisfeiler-Lehman Graph Kernels

This repository contains the accompanying code for the NeurIPS 2019 paper Wasserstein Weisfeiler-Lehman Graph Kernels available here. The repository contains both the package that implements the graph kernels (in src) and scripts to reproduce some of the results of the paper (in experiments).


WWL relies on the following dependencies:

  • numpy
  • scikit-learn
  • POT
  • cython


The easiest way is to install WWL from the Python Package Index (PyPI) via

$ pip install Cython numpy 
$ pip install wwl


The WWL package contains functions to generate a n x n kernel matrix between a set of n graphs.

The API also allows the user to directly call the different steps described in the paper, namely:

  • generate the embeddings for the nodes of both discretely labelled and continuously attributed graphs,
  • compute the pairwise distance between a set of graphs

Please refer to the src README for detailed documentation.


You can find some experiments in the experiments folder. These will allow you to reproduce results from the paper on 2 datasets.


WWL is developed and maintained by members of the Machine Learning and Computational Biology Lab:


Please use the following BibTeX citation when using our method or comparing against it:

  author        = {Togninalli, Matteo and Ghisu, Elisabetta and Llinares-López, Felipe and Rieck, Bastian and Borgwardt, Karsten},
  title         = {Wasserstein Weisfeiler--Lehman Graph Kernels},
  booktitle     = {Advances in Neural Information Processing Systems 32},
  year          = {2019},
  pubstate      = {forthcoming},
  eprint        = {1906.01277},
  archiveprefix = {arXiv},
  author+an     = {4=highlight},
  primaryclass  = {cs.LG},
You can’t perform that action at this time.