Code for the paper: "Graph Self Supervised Learning: the BT, the HSIC, and the VICReg" (Paper accepted in the Weakly Supervised Representation Learning Workshop, IJCAI 2021 (IJCAI2021-WSRL))
Paper link: https://arxiv.org/abs/2105.12247
Install required packages
$ pip install -q torch-scatter -f https://pytorch-geometric.com/whl/torch-1.8.0+cu101.html
$ pip install -q torch-sparse -f https://pytorch-geometric.com/whl/torch-1.8.0+cu101.html
$ pip install -q torch-geometric
Citation
@article{nag2021graphvicreghsic,
title={GraphVICRegHSIC: Towards improved self-supervised representation learning for graphs with a hyrbid loss function},
author={Nag, Sayan},
journal={arXiv e-prints},
pages={arXiv--2105},
year={2021}
}