search

pyg-team / pytorch_geometric

Graph Neural Network Library for PyTorch
https://pyg.org
MIT License
20.91k stars 3.61k forks source link

Request to add two graph self-supervised methods #1773

Open yyou1996 opened 3 years ago

yyou1996 commented 3 years ago

🚀 Feature

Request to add two graph self-supervised methods to Pytorch Geometric: (1) heuristic designed graph self-supervised tasks (ICML'20): https://arxiv.org/abs/2006.09136; code: https://github.com/Shen-Lab/SS-GCNs; (2) contrastive learning as self-supervision (NeurIPS'20): https://arxiv.org/abs/2010.13902; code: https://github.com/Shen-Lab/GraphCL.

Motivation

Self-supervision as an emerging technique has been employed to train graph neural networks (GNNs) for more transferrable, generalizable, and robust representation learning of graphs.

Additional context

rusty1s commented 3 years ago

Thanks, I will look into it. Feel free to contribute if you like :)

kou18n commented 1 year ago

@rusty1s Hello, I implemented the GraphCL model with sparse_tesnor support. I use the PyGCL code, and rewrite some code. Currently, I think PyG can not support the contrastive learning model. How should I contribute it to PyG?

rusty1s commented 1 year ago

That sounds cool :) We are very happy to take a pull request in on that one, including both the model and an example. Let me know if you have any questions.