why986/Graph_Transformer_Networks

Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

Graph Transformer Networks

This repository is the implementation of Graph Transformer Networks(GTN).

Seongjun Yun, Minbyul Jeong, Raehyun Kim, Jaewoo Kang, Hyunwoo J. Kim, Graph Transformer Networks, In Advances in Neural Information Processing Systems (NeurIPS 2019).

Dependencies

• Python 3.6+
• PyTorch 1.1.0+
• Pytorch_geometric 1.3.1

Data Preprocessing

We used datasets from Heterogeneous Graph Attention Networks (Xiao Wang et al.) and uploaded the preprocessing code of acm data as an example.

Running the code

$ mkdir data
$ cd data

Download datasets (DBLP, ACM, IMDB) from this link and extract data.zip into data folder.

$ cd ..

• DBLP

$ python main.py --dataset DBLP --num_layers 3

• ACM

 $ python main.py --dataset ACM --num_layers 2 --adaptive_lr true

• IMDB

 $ python main_sparse.py --dataset IMDB --num_layers 3 --adaptive_lr true

Citation

If this work is useful for your research, please cite our paper:

@inproceedings{yun2019graph,
  title={Graph Transformer Networks},
  author={Yun, Seongjun and Jeong, Minbyul and Kim, Raehyun and Kang, Jaewoo and Kim, Hyunwoo J},
  booktitle={Advances in Neural Information Processing Systems},
  pages={11960--11970},
  year={2019}
}