View Code? Open in Web Editor
NEW
[CIKM 2023] GUARD: Graph Universal Adversarial Defense
Jupyter Notebook 39.70%
Python 60.30%
guard's Introduction
- Sun Yat-sen University, China
- Major in Software Engineering
- Learning Python, Machine Learning
- TensorFlow and PyTorch Enthusiast
- Graph Representation Learning
- Trustworthy Graph Learning
- Graph Self-supervised Learning
- GraphGallery: Graph Gallery for benchmarking graph neural networks
- GreatX (ongoing): Graph reliability toolbox based on PyTorch Geometric
- Mooon (ongoing): Graph data augmentation library based on PyTorch Geometric
guard's People
Contributors
guard's Issues
您好,我在阅读您的文章时发现一个问题,当使用clean graph的degree作为模型的输入时,获得的defense效果要比使用attacked graph的degree作为模型输入好上不少,您是否也注意到过这个问题呢,对于这个结果您怎么看,只是想和您探讨一下,期待您的回复!
Hi, I do not see any requirement to install torch geometric. So when I ran your demo.ipynb, it caused an error
'No module named 'torch_geometric.nn.dense.linear'
What is the version of torch geometric you used for this repo? I'm using torch geometric 1.7.0
Thanks