Skip to content

asFeng/kergnns

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

This repository is the official PyTorch implementation of "KerGNNs: Interpretable Graph Neural Networks with Graph Kernels", Aosong Feng, Chenyu You, Shiqiang Wang, Leandros Tassiulas, AAAI 2022 [link] (https://arxiv.org/abs/2201.00491).

Installation

Install PyTorch following the instuctions on the [official website] (https://pytorch.org/). The code has been tested over PyTorch 1.6.0 version.

Then install the other dependencies.

pip install -r requirements.txt

Datasets

All the dataset are downloaded from

https://ls11-www.cs.tu-dortmund.de/staff/morris/graphkerneldatasets

The data spilts are the same with here.

Test Run

  • 1-layer KerGNN with random walk graph kernel, IMDB-BINARY dataset
python main.py --iter 0
  • 2-layer KerGNN with deep random walk kernel, PROTEINS-full dataset
python main.py --iter 0 --dataset PROTEINS_full --kernel drw --hidden_dims 0 16 32 --size_graph_filter 4 4 --use_node_labels --no_norm

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages