Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
configs		configs
data		data
layers		layers
misc		misc
nets		nets
scripts		scripts
train		train
LICENSE		LICENSE
README.md		README.md
main_SBMs_node_classification.py		main_SBMs_node_classification.py
main_ZINC_graph_regression.py		main_ZINC_graph_regression.py
main_molhiv.py		main_molhiv.py
requirements.txt		requirements.txt

Repository files navigation

SAN

We present Spectral Attention Networks, a power GNN that leverages key principles from spectral graph theory to enable full graph attention.

nets contains the Node, Edge and no LPE architectures implemented with PyTorch.
layers contains the multi-headed attention employed by the Main Graph Transformer implemented in DGL.
configs contains the various parameters used in the ablation and SOTA comparison studies
train contains methods to train the models
docs contains scripts from https://github.com/graphdeeplearning/graphtransformer to download datasets and setup environments.
scripts contains scripts to reproduce ablation and SOTA comparison results. See scripts/reproduce.md for details.