/PTDNet

Learning to Drop: Robust Graph Neural Network via Topological Denoising & Robust Graph Representation Learning via Neural Sparsification

Primary LanguagePython

PTDNet

This is a Tensorflow implementation of paper: Learning to Drop: Robust Graph Neural Network via Topological Denoising

https://arxiv.org/abs/2011.07057

WSDM'21

Unofficial Implementation Robust Graph Representation Learning via Neural Sparsification

ICML 20

Since the previous version is not easy to use, I've updated the code from Tensorflow 1.0 to Tensorflow 2.0. Currently, I only provide sample implementation for reference. Hyper-parameters for different datasets need tune.

Requirements

  • Python 3.8.6
  • tensorflow 2.3.1
  • networkx

References

@inproceedings{luo2021learning,
  title={Learning to Drop: Robust Graph Neural Network via Topological Denoising},
  author={Luo, Dongsheng and Cheng, Wei and Yu, Wenchao and Zong, Bo and Ni, Jingchao and Chen, Haifeng, and Zhang, Xiang},
  booktitle={Proceedings of the 14th ACM International Conference on Web Search and Data Mining},
  year={2021},
  organization={ACM}
}