View Code? Open in Web Editor
NEW
This is a PyTorch implementation of the GeniePath model in <GeniePath: Graph Neural Networks with Adaptive Receptive Paths> (https://arxiv.org/abs/1802.00910)
Home Page: https://github.com/pyg-team/pytorch_geometric/blob/master/examples/geniepath.py
License: MIT License
geniepath-pytorch's People
Contributors
Watchers
geniepath-pytorch's Issues
hello, thanks for your great work !
I am wondering where is the skip connection in the "GeniePath-lazy" model ?
这里的PPI设定和GAT文章里的一样吗?为什么GAT里PPI能达到97.3,这篇文章只报了81?
After the first epoch both your model result in NAN loss. I am using P100 and havs anyone encountered this problem before?
I can't find any code of the part about "Efficient Numerical Computation" proposed in your paper.
实际运行时,
使用“from model_geniepath import GeniePath as Net”作为网络模型,只能得到0.45的f1-score。
而README.md说能达到0.9709,请问是需要设置一些参数吗?谢谢