https://github.com/junxia97/ProGCL

[ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"
https://github.com/junxia97/ProGCL

contrastive-learning graph-neural-networks graph-self-supervised-learning hard-negative-mining icml-2022

Last synced: 3 months ago
JSON representation

[ICML 2022] "ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning"

• Host: GitHub
• URL: https://github.com/junxia97/ProGCL
• Owner: junxia97
• Created: 2022-05-15T08:46:00.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2022-06-13T12:18:21.000Z (over 2 years ago)
• Last Synced: 2024-05-13T22:52:55.566Z (9 months ago)
• Topics: contrastive-learning, graph-neural-networks, graph-self-supervised-learning, hard-negative-mining, icml-2022
• Language: Python
• Homepage:
• Size: 33.2 KB
• Stars: 39
• Watchers: 1
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Awesome-Mixup - [Code

README

        
# ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning (ICML 2022)

PyTorch implementation for [ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning](https://arxiv.org/abs/2110.02027) accepted by ICML 2022.

## Requirements

* Python 3.7.4

* PyTorch 1.7.0

* torch_geometric 1.5.0

* tqdm

## Training & Evaluation

ProGCL-weight:

```

python train.py --device cuda:0 --dataset Amazon-Computers --param local:amazon-computers.json --mode weight

```

ProGCL-mix:

```

python train.py --device cuda:0 --dataset Amazon-Computers --param local:amazon-computers.json --mode mix

```

## Useful resources for Pretrained Graphs Neural Networks

* The first comprehensive survey on this topic: [A Survey of Pretraining on Graphs: Taxonomy, Methods, and Applications](https://arxiv.org/abs/2202.07893v1)

* [A curated list of must-read papers, open-source pretrained models and pretraining datasets.](https://github.com/junxia97/awesome-pretrain-on-graphs)

## Citation

```

@inproceedings{xia2022progcl,

  title={ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning},

  author={Xia, Jun and Wu, Lirong and Wang, Ge and Li, Stan Z.},

  booktitle={International conference on machine learning},

  year={2022},

  organization={PMLR}

}

```