Skip to content

Files

This branch is 257 commits behind dmlc/dgl:master.

gat

Graph Attention Networks (GAT)

Note that the original code is implemented with Tensorflow for the paper.

Dependencies

  • MXNet nightly build
  • requests
pip install mxnet --pre
pip install requests

Usage (make sure that DGLBACKEND is changed into mxnet)

DGLBACKEND=mxnet python3 train.py --dataset cora --gpu 0
DGLBACKEND=mxnet python3 train.py --dataset citeseer --gpu 0 --early-stop
DGLBACKEND=mxnet python3 train.py --dataset pubmed --gpu 0 --early-stop