Openhgnn

1. New models and datasets.
2. 4 New tasks : pretrain, recommendation, graph attacks and defenses, abnorm_event detection.
3. TensorBoard visualization.
4. Maintenance and testing.

1. New models
2. Provide pipelines for applications
3. More models supporting mini-batch training
4. Benchmark for million-scale graphs

1. New models
2. API usage
3. Customization of datasets and models

1. New models
2. Space4HGNN
3. Benchmark & Leaderboard

1. Release v0.1.1 on [OpenI](https://git.openi.org.cn/GAMMALab/OpenHGNN) with Chinese.
2. Add more models.
3. Add logger feature.
4. More models implemented in link prediction

The first open release includes basically everything in the repository.

Docs: a tutorial for basic and depth usage.
Models: 16 HGNN models