Skip to content
/ gcn Public
forked from tkipf/gcn

Implementation of Graph Convolutional Networks in TensorFlow

License

Notifications You must be signed in to change notification settings

harveybi/gcn

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

26 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Graph Convolutional Networks

This is a TensorFlow implementation of Graph Convolutional Networks for the task of (semi-supervised) classification of nodes in a graph, as described in our paper:

Thomas N. Kipf, Max Welling, Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017)

For a high-level explanation, have a look at our blog post:

Thomas Kipf, Graph Convolutional Networks (2016)

Installation

python setup.py install

Requirements

  • tensorflow (>0.12)
  • networkx

Run the demo

python train.py

Data

In order to use your own data, you have to provide

  • an N by N adjacency matrix (N is the number of nodes),
  • an N by D feature matrix (D is the number of features per node), and
  • an N by E binary label matrix (E is the number of classes).

Have a look at the load_data() function in utils.py for an example.

In this example, we load citation network data (Cora, Citeseer or Pubmed). The original datasets can be found here: http://linqs.cs.umd.edu/projects/projects/lbc/. In our version (see data folder) we use dataset splits provided by https://github.com/kimiyoung/planetoid (Zhilin Yang, William W. Cohen, Ruslan Salakhutdinov, Revisiting Semi-Supervised Learning with Graph Embeddings, ICML 2016).

You can specify a dataset as follows:

python train.py --dataset citeseer

(or by editing train.py)

Models

You can choose between the following models:

Graph classification

Our framework also supports batch-wise classification of multiple graph instances (of potentially different size) with an adjacency matrix each. It is best to concatenate respective feature matrices and build a (sparse) block-diagonal matrix where each block corresponds to the adjacency matrix of one graph instance. For pooling (in case of graph-level outputs as opposed to node-level outputs) it is best to specify a simple pooling matrix that collects features from their respective graph instances, as illustrated below:

graph_classification

Cite

Please cite our paper if you use this code in your own work:

@inproceedings{kipf2017semi,
  title={Semi-Supervised Classification with Graph Convolutional Networks},
  author={Kipf, Thomas N. and Welling, Max},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2017}
}

About

Implementation of Graph Convolutional Networks in TensorFlow

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%