CogDL is a graph representation learning toolkit that allows researchers and developers to easily train and compare baseline or custom models for node classification, link prediction and other tasks on graphs. It provides implementations of many popular models, including:
- non-GNN Baselines like Deepwalk, LINE, NetMF;
- GNN Baselines like GCN, GAT, GraphSAGE.
Requirements and Installation
- TensorFlow version >= 2.0.0
- Python version >= 3.6
pip install -e .
You can use
python scripts/train.py --task example_task --dataset example_dataset --model example_method to run example_method on example_data and evaluate it via example_task.
CogDL-TensorFlow is still under planning. Guys who are interesting in working on this project, welcome to add my wechat below and join our discussion group.