https://github.com/borgwardtlab/wwl
Wasserstein Weisfeiler-Lehman Graph Kernels
https://github.com/borgwardtlab/wwl
Last synced: about 1 year ago
JSON representation
Wasserstein Weisfeiler-Lehman Graph Kernels
- Host: GitHub
- URL: https://github.com/borgwardtlab/wwl
- Owner: BorgwardtLab
- License: bsd-3-clause
- Created: 2019-10-02T11:36:39.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2024-09-01T15:42:08.000Z (over 1 year ago)
- Last Synced: 2025-03-24T11:46:02.966Z (about 1 year ago)
- Language: Python
- Homepage:
- Size: 10.1 MB
- Stars: 81
- Watchers: 5
- Forks: 19
- Open Issues: 4
-
Metadata Files:
- Readme: README.md
- License: LICENSE
- Support: supporting_material/Poster.pdf
Awesome Lists containing this project
README
# Wasserstein Weisfeiler-Lehman Graph Kernels
This repository contains the accompanying code for the NeurIPS 2019 paper
_Wasserstein Weisfeiler-Lehman Graph Kernels_ available
[here](http://papers.nips.cc/paper/8872-wasserstein-weisfeiler-lehman-graph-kernels).
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`).
## Dependencies
WWL relies on the following dependencies:
- `numpy`
- `scikit-learn`
- `POT`
- `cython`
## Installation
The easiest way is to install WWL from the Python Package Index (PyPI) via
```sh
$ pip install Cython numpy
$ pip install wwl
```
## Usage
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](https://github.com/BorgwardtLab/WWL/blob/master/src) for detailed documentation.
## Experiments
You can find some experiments in the [experiments folder](https://github.com/BorgwardtLab/WWL/blob/master/experiments). These will allow you to reproduce results from the paper on 2 datasets.
## Contributors
WWL is developed and maintained by members of the [Machine Learning and
Computational Biology Lab](https://www.bsse.ethz.ch/mlcb):
- Matteo Togninalli ([GitHub](https://github.com/mtog))
- Elisabetta Ghisu ([Github](https://github.com/eghisu))
- Bastian Rieck ([GitHub](https://github.com/Pseudomanifold))
## Citation
Please use the following BibTeX citation when using our method or comparing against it:
```
@InCollection{Togninalli19,
author = {Togninalli, Matteo and Ghisu, Elisabetta and Llinares-L{\'o}pez, Felipe and Rieck, Bastian and Borgwardt, Karsten},
title = {Wasserstein Weisfeiler--Lehman Graph Kernels},
booktitle = {Advances in Neural Information Processing Systems~32~(NeurIPS)},
year = {2019},
editor = {Wallach, H. and Larochelle, H. and Beygelzimer, A. and d'Alch\'{e}{-}Buc, F. and Fox, E. and Garnett, R.},
publisher = {Curran Associates, Inc.},
pages = {6436--6446},
}
```