Welcome to OpenHGNN’s documentation!

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL [Deep Graph Library] and PyTorch. We integrate SOTA models of heterogeneous graph.

Key Features

• Easy-to-Use: OpenHGNN provides easy-to-use interfaces for running experiments with the given models and datasets using optuna which is a hyperparameter optimization framework.

• Extensibility: User can define customized task/model/dataset to apply new models to new scenarios.

• Efficiency: The backend dgl provides efficient APIs.

Contract Us

If you have any question, please submit issues or contact us: tyzhao@bupt.edu.cn