Home

Awesome

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

PyTorch implementation for ProGCL: Rethinking Hard Negative Mining in Graph Contrastive Learning accepted by ICML 2022.

Requirements

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

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}
}