Example regression GNN architecture for homogeneous graph and node level prediction

pyg-team / pytorch_geometric

Graph Neural Network Library for PyTorch

https://pyg.org

MIT License

20.91k stars 3.61k forks source link

Example regression GNN architecture for homogeneous graph and node level prediction #9041

Open MICMTS opened 6 months ago

MICMTS commented 6 months ago

🚀 The feature, motivation and pitch

Hello,

I would like to know if there is any example/tutorial available to build a GNN model (layers architecture) with Pytorch Geometric for a regression task using homogeneous graph and node level prediction?

I did not understood fully the suggestion in: https://github.com/pyg-team/pytorch_geometric/issues/3794

Thank you in advance!

Alternatives

No response

Additional context

No response

rusty1s commented 6 months ago

I can't think of an example on top of my head, but usually it is not hart to convert a node classification task to a node regression task. It usually only involves changing the loss function.