pyg-team / pytorch_geometric

Graph Neural Network Library for PyTorch
https://pyg.org
MIT License
21.35k stars 3.66k forks source link

K-fold cross validation for GCNs in PyTorch Geometric #3663

Closed bianchiniriccardo95 closed 2 years ago

bianchiniriccardo95 commented 2 years ago

Hello! First of all, thanks for this amazing tool. I have a question: I want to perform node classification on my network composed of 2410 nodes. Since now, I split my nodes using the function AddTrainValTestMask function in order to validate the machine, but my idea is to perform a K-fold cross validation of the network, to gain better confidence about the goodness of the GCN. How can I do this? How can I split my nodes in the different masks multiple times? Is there a specific function? Thanks in advance.

rusty1s commented 2 years ago

https://github.com/pyg-team/pytorch_geometric/discussions/3662