pub_soft/dgl

mirror of https://github.com/dmlc/dgl.git synced 2026-06-03 19:34:33 +08:00

Files

History

Zhen Liu 15d05be387 Fix num_labels to num_classes in dataset files (#6666 )

2023-12-04 13:25:44 +08:00

..

gat.py

examples (#5323 )

2023-02-19 08:35:15 +08:00

README.md

[Dataset] Citation graph (#1902 )

2020-08-01 19:25:50 +08:00

train.py

Fix num_labels to num_classes in dataset files (#6666 )

2023-12-04 13:25:44 +08:00

utils.py

[Misc] Black auto fix. (#4679 )

2022-10-08 11:59:37 +08:00

README.md

Graph Attention Networks (GAT)

Paper link: https://arxiv.org/abs/1710.10903
Author's code repo (in Tensorflow): https://github.com/PetarV-/GAT.
Popular pytorch implementation: https://github.com/Diego999/pyGAT.

Dependencies

tensorflow 2.1.0+
requests

pip install tensorflow requests
DGLBACKEND=tensorflow

How to run

Run with following:

python3 train.py --dataset=cora --gpu=0

python3 train.py --dataset=citeseer --gpu=0 --early-stop

python3 train.py --dataset=pubmed --gpu=0 --num-out-heads=8 --weight-decay=0.001 --early-stop

Results

Dataset	Test Accuracy	Baseline (paper)
Cora	84.2	83.0(+-0.7)
Citeseer	70.9	72.5(+-0.7)
Pubmed	78.5	79.0(+-0.3)

All the accuracy numbers are obtained after 200 epochs.
All time is measured on EC2 p3.2xlarge instance w/ V100 GPU.