This example shows how to use modules defined in dgl.nn.pytorch.conv to do node classification on
citation network datasets.
- Cora
- Citeseer
- Pubmed
- GCN: Semi-Supervised Classification with Graph Convolutional Networks
- GAT: Graph Attention Networks
- GraphSAGE Inductive Representation Learning on Large Graphs
- APPNP: Predict then Propagate: Graph Neural Networks meet Personalized PageRank
- GIN: How Powerful are Graph Neural Networks?
- TAGCN: Topology Adaptive Graph Convolutional Networks
- SGC: Simplifying Graph Convolutional Networks
- AGNN: Attention-based Graph Neural Network for Semi-supervised Learning
- ChebNet: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
python run.py [--gpu GPU] --model MODEL_NAME --dataset DATASET_NAME [--self-loop]
The hyperparameters might not be the optimal, you could specify them manually in conf.py.