chengtaicao / meta-gnn Goto Github PK

Thanks for open-sourcing!

I am learning your code and I couldn't find the code for GNN learner in the learner.py class in the meta GNN folder, it looks like it only uses the linear layer. I am wondering could you point it to me where the GCN layer is used for the base learner class?

Thank you!

According to your code, when generating a meta task, no matter what the n-way is, it will generate a 2-way data.

When I ran the sgc.py in the meta_gnn folder, I found both the training accuracy and testing accuracy are 0 in all cases.

Dear Authors,
May I ask about accuracy from your codes
Step: 0 Meta_Training_Accuracy: [0.25833333 0.34166667 0.41666667 0.45 0.46666667 0.50833333
0.54166667 0.55833333 0.6 0.64166667 0.675 ]
why the length of list is 1+update_step and what is the meaning of each acc[i]?
how I evaluate the model is good or not from accuracy?
thanks,