Zhanghyi / OpenHGNN

This is an open-source toolkit for Heterogeneous Graph Neural Network(OpenHGNN) based on DGL.

OpenHGNN

启智社区（中文版） | Space4HGNN [SIGIR2022] | Benchmark&Leaderboard

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

News

2021-02-28

We release the latest version v0.2.

• New Models
• Space4HGNN [SIGIR2022]
• Benchmark&Leaderboard

2021-01-07

启智社区用户可以享受到如下功能：

• 全新的中文文档
• 免费的计算资源
• OpenHGNN最新功能

Key Features

• Easy-to-Use: OpenHGNN provides easy-to-use interfaces for running experiments with the given models and dataset. Besides, we also integrate optuna to get hyperparameter optimization.
• Extensibility: User can define customized task/model/dataset to apply new models to new scenarios.
• Efficiency: The backend dgl provides efficient APIs.

Get Started

Requirements and Installation

• Python >= 3.6

• PyTorch >= 1.9.0

• DGL >= 0.8.0

• CPU or NVIDIA GPU, Linux, Python3

1. Python environment (Optional): We recommend using Conda package manager

conda create -n openhgnn python=3.7
source activate openhgnn

2. Install Pytorch: Follow their tutorial to run the proper command according to your OS and CUDA version. For example:

pip install torch torchvision torchaudio

3. Install DGL: Follow their tutorial to run the proper command according to your OS and CUDA version. For example:

pip install dgl dglgo -f https://data.dgl.ai/wheels/repo.html

4. OpenHGNN and other dependencies:

git clone https://github.com/BUPT-GAMMA/OpenHGNN
# If you encounter a network error, try git clone from openi as following.
# git clone https://git.openi.org.cn/GAMMALab/OpenHGNN.git
cd OpenHGNN
pip install -r requirements.txt

Running an existing baseline model on an existing benchmark dataset

python main.py -m model_name -d dataset_name -t task_name -g 0 --use_best_config --load_from_pretrained

usage: main.py [-h] [--model MODEL] [--task TASK] [--dataset DATASET] [--gpu GPU] [--use_best_config]

optional arguments:

-h, --help show this help message and exit

--model -m name of models

--task -t name of task

--dataset -d name of datasets

--gpu -g controls which gpu you will use. If you do not have gpu, set -g -1.

--use_best_config use_best_config means you can use the best config in the dataset with the model. If you want to set the different hyper-parameter, modify the openhgnn.config.ini manually. The best_config will override the parameter in config.ini.

--use_hpo Besides use_best_config, we give a hyper-parameter example to search the best hyper-parameter automatically.

--load_from_pretrained will load the model from a default checkpoint.

e.g.:

python main.py -m GTN -d imdb4GTN -t node_classification -g 0 --use_best_config

Note: If you are interested in some model, you can refer to the below models list.

Refer to the docs to get more basic and depth usage.

Models

Supported Models with specific task

The link will give some basic usage.

Model	Node classification	Link prediction	Recommendation
Metapath2vec[KDD 2017]	✔️
RGCN[ESWC 2018]	✔️	✔️
HERec[TKDE 2018]	✔️
HAN[WWW 2019]	✔️	✔️
KGCN[WWW 2019]			✔️
HetGNN[KDD 2019]	✔️	✔️
HGAT[EMNLP 2019]
GTN[NeurIPS 2019] & fastGTN	✔️
RSHN[ICDM 2019]	✔️	✔️
DMGI[AAAI 2020]	✔️
MAGNN[WWW 2020]	✔️
HGT[WWW 2020]	✔️
CompGCN[ICLR 2020]	✔️	✔️
NSHE[IJCAI 2020]	✔️
NARS[arxiv]	✔️
MHNF[arxiv]	✔️
HGSL[AAAI 2021]	✔️
HGNN-AC[WWW 2021]	✔️
HeCo[KDD 2021]	✔️
SimpleHGN[KDD 2021]	✔️
HPN[TKDE 2021]	✔️	✔️
RHGNN[arxiv]	✔️
HDE[ICDM 2021]		✔️
GATNE-T[KDD 2019]		✔️

Candidate models

• Heterogeneous Graph Attention Networks for Semi-supervised Short Text Classification[EMNLP 2019]
• Heterogeneous Information Network Embedding with Adversarial Disentangler[TKDE 2021]

Contributors

OpenHGNN Team[GAMMA LAB], DGL Team and Peng Cheng Laboratory.

See more in CONTRIBUTING.