README

This is the code for paper Training Free Graph Neural Networks for Graph Matching. arXiv preprint.

Dependencies

  1. PyTorch
  2. Pytorh Geometric 1.7.0

Datasets

Download the DBP15k and the PPI dataset from this Onedrive Link. Unzip the file in the data folder.

PascalVOC will be downloaded automatically when running codes.

Reproduce results in paper

Pascal

>> python pascal.py --use_splinecnn --use_knn --use_dgmc --gpu_id 0

DBP15k

>> python dbp15k.py --dataset zh_en --use_dgmc --use_supervision --weight_free --gpu_id 0

PPI

>> python ppi.py --dataset extra_edge --use_dgmc --num_steps 100  --weight_free --rnd_dim 128 --gpu_id 0

Reference

If you use our code, please cite our paper

@article{liu2022training,
  title={Training Free Graph Neural Networks for Graph Matching},
  author={Liu, Zhiyuan and Cao, Yixin and Feng, Fuli and Wang, Xiang and Shang, Xindi and Tang, Jie and Kawaguchi, Kenji and Chua, Tat-Seng},
  journal={arXiv preprint},
  year={2022}
}

GitHub

View Github