Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add new node(s) to the graph with trained model. #401

Open
cappelchi opened this issue Oct 26, 2022 · 3 comments
Open

Add new node(s) to the graph with trained model. #401

cappelchi opened this issue Oct 26, 2022 · 3 comments

Comments

@cappelchi
Copy link

Could someone suggest, how to add new node(s) to the single graph, that already has trained model for node classification, to make prediction(classification) for this new nodes with existing model?

@danielegrattarola
Copy link
Owner

Sorry for the late reply but for some reason I stopped receiving notifications.

Have you tried just adding the new node to the graph and doing the prediction? The model will work even if you add nodes at training time

@cappelchi
Copy link
Author

But it means I can't use the pretrained model in single mode in production? New nodes need training.

@danielegrattarola
Copy link
Owner

New nodes need training.

I'm not sure what you mean by this. The GNN will be able to make predictions for new nodes because of its node-level local processing. You don't need to retrain the model everytime you add/remove nodes, that's a big part of what makes GNNs interesting.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants