https://github.com/alge24/eigenpooling
An implementation of KDD paper "Graph Convolutional Networks with EigenPooling"
https://github.com/alge24/eigenpooling
Last synced: about 2 months ago
JSON representation
An implementation of KDD paper "Graph Convolutional Networks with EigenPooling"
- Host: GitHub
- URL: https://github.com/alge24/eigenpooling
- Owner: alge24
- Created: 2019-11-30T21:24:55.000Z (over 5 years ago)
- Default Branch: master
- Last Pushed: 2019-12-02T04:37:37.000Z (over 5 years ago)
- Last Synced: 2024-10-30T14:43:28.372Z (7 months ago)
- Language: Python
- Size: 3.49 MB
- Stars: 47
- Watchers: 4
- Forks: 15
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
- awesome-graph-classification - [Python Reference
README
# Graph Convolutional Networks with EigenPooling
Pytorch implementation of [eigenpooling](https://arxiv.org/pdf/1904.13107.pdf). Some parts of the code are adapdted from the implementation of [diffpool](https://github.com/RexYing/diffpool).
For more details of the algorithm, please refer to our [paper](https://arxiv.org/pdf/1904.13107.pdf). If you find this work useful and use it in your research, please cite our paper.
```
@inproceedings{Ma:2019:GCN:3292500.3330982,
author = {Ma, Yao and Wang, Suhang and Aggarwal, Charu C. and Tang, Jiliang},
title = {Graph Convolutional Networks with EigenPooling},
booktitle = {Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery \& Data Mining},
series = {KDD '19},
year = {2019},
isbn = {978-1-4503-6201-6},
location = {Anchorage, AK, USA},
pages = {723--731},
numpages = {9},
url = {http://doi.acm.org/10.1145/3292500.3330982},
doi = {10.1145/3292500.3330982},
acmid = {3330982},
publisher = {ACM},
address = {New York, NY, USA},
keywords = {graph classification, graph convolution networks, pooling, spectral graph theory},
}
```
#### Usage
Please check run_example.sh for an example of running the code.
#### Preprocessed datasets
You may download the preprocessed datasets [here](https://drive.google.com/open?id=1-8FrJxWFczCAnhOWVi9fq0SdwpA7pM_p) to save the time of preprocessing data.
#### Known Issue
Running on GPU may result in sub-optimal performance on some of the datasets inclduing ENZYMES, NCI1 and NCI109.