Skip to content
/ PyGNN Public

Official Implementation of KDD 2023 paper: "Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations"

License

Notifications You must be signed in to change notification settings

hygeng/PyGNN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PyGNN

Publication PRs License Stars

Official Implementation of KDD 2023 paper:
"Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations"

PyGNN

We propose Pyramid Graph Neural Network framework(PyGNN), a multi-scale framework for node representations on graphs.
More details are shown in this project.

Environment Settings

* pytorch               1.7.0    
* numpy                 1.18.1    
* torch-geometric       1.7.0    
* torch-cluster         1.6.0    
* torch-scatter         2.0.5    
* torch-sparse          0.6.8    
* torch-spline-conv     1.2.0    
* scipy                 1.6.2    

(The currently used dataset may not support later torch-geometric versions.)

Run

  1. set "TOP_DIR" as dataset directory in src/dataloader.py (provided in "./dataset/")
  2. Generate Pyramid subgraphs (provided)
python src/proc/Downsample.py -d ${dataname}
python src/proc/post_proc.py -d ${dataname} -s Downsample
  1. run:
bash node.sh

Citation

If you use our implementation in your works, we would appreciate citations to the paper:

@inproceedings{geng2023pyramid,
    author = {Geng, Haoyu and Chen, Chao and He, Yixuan and Zeng, Gang and Han, Zhaobing and Chai, Hua and Yan, Junchi},
    title = {Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-Scale Disentangled Representations},
    year = {2023},
    isbn = {9798400701030},
    publisher = {Association for Computing Machinery},
    address = {New York, NY, USA},
    url = {https://doi.org/10.1145/3580305.3599478},
    doi = {10.1145/3580305.3599478},
    booktitle = {Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
    pages = {518–530},
    numpages = {13},
    keywords = {graph algorithms, spectral graph theory, graph neural networks},
    location = {Long Beach, CA, USA},
    series = {KDD '23}
}

About

Official Implementation of KDD 2023 paper: "Pyramid Graph Neural Network: A Graph Sampling and Filtering Approach for Multi-scale Disentangled Representations"

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published