CS 6787 Final Project: Graph Convolutional Network Analysis

In this repository we implement a Graph Convolutional Network using exclusively python primitives and compare its performance with Thomas N. Kipf, Max Welling, Semi-Supervised Classification with Graph Convolutional Networks (ICLR 2017)'s TensorFlow and Pytorch implementation.

For more information on Graph Convolutional networks see GCN

Numpy Implementation

python numpyGCN/train.py

TensorFlow Implementation

First run...

python tfGCN/setup.py install

and then

python tfGCN/train.py

PyTorch Implementation

python torchGCN/train.py