GCN

Model description

GCN(Graph Convolutional Networks) was proposed in 2016 and designed to do semi-supervised learning on graph-structured data. A scalable approach based on an efficient variant of convolutional neural networks which operate directly on graphs was presented. The model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes.

Paper: Thomas N. Kipf, Max Welling. 2016. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR 2016.

Step 1:Installation

# Clone PGL repository
git clone https://github.com/PaddlePaddle/PGL.git

# Pip the requirements
pip3 install pgl
pip3 install urllib3==1.23
pip3 install networkx

Step 2:Preparing datasets

Datasets are called in the code.

The datasets contain three citation networks: CORA, PUBMED, CITESEER.

Step 3:Training

cd PGL/examples/gcn/

# Run on CPU
python3 train.py --dataset cora

# Run on GPU
CUDA_VISIBLE_DEVICES=0 python3 train.py --dataset cora

Results

Reference

PGL/GCN