This repository contains the reference code for the paper Simple Unsupervised Graph Representation Learning
pip install -r requirements.txt
Pretrained model see >>>here<<<.
Configs see >>>here<<<.
Dataset (--dataset-class
, --dataset-name
,--Custom-key
)
Dataset class | Dataset name | Custom key |
---|---|---|
Planetoid | Cora | classification |
Planetoid | CiteSeer | classification |
Planetoid | PubMed | classification |
MyAmazon | Photo | classification |
MyAmazon | Computers | classification |
PygNodePropPredDataset | ogbn-arxiv | classification |
PygNodePropPredDataset | ogbn-mag | classification |
PygNodePropPredDataset | ogbn-products | classification |
Important args:
--pretrain
Test checkpoints--dataset-class
Planetoid, MyAmazon, PygNodePropPredDataset--dataset-name
Cora, CiteSeer, PubMed, Photo, Computers, ogbn-arxiv, ogbn-mag, ogbn-products--custom_key
classification, link, clu
python train.py
Choose the custom_key of different downstream tasks
@InProceedings{Mo_AAAI_2022,
title={Simple Unsupervised Graph Representation Learning},
booktitle={Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)},
author={Mo, Yujie and Peng, Liang and Xu, Jie and Shi, Xiaoshuang and Zhu, Xiaofeng},
year={2022},
pages={7797-7805}
}