-
Hi,
I was just wondering if there was an implicit use of unlabelled data in the process of transductive fine-tuning in the baseline paper. This is because transductive fine-tuning uses the batch no…
-
Hi danielegrattarola，great works!
But the classification accuracy for the transductive task on dataset cora is always approximately 80%~81%. I scrutimize the source code and keep the (hyper-)paramete…
-
Your code doesn't shuffle the relative position of data. For example, in 5-way 1-shot, suppose in index 1-5 corresponds to label 1-5, then index 6 must belong to label 1, index 7 is label2..... So, is…
-
Hi,
I am trying to use there 3 methods, but my graph is not connected:
site-packages/karateclub/estimator.py", line 50, in _check_connectivity
raise ValueError("Graph is not connected. Please s…
-
Hi, I have trained model but I am not able to use trained weights and model for prediction( inference ) time.
Can you provide simple example for that?
Thank you !
-
@thomasjpfan By building the documentation from scratch I have the following issue:
```
ARNING: the custom_autosummary_new_suffix extension does not declare if it is safe for parallel reading, ass…
-
It seems in GNN(graph neural network), in transductive situation, we input the whole graph and we mask the label of valid data and predict the label for the valid data.
But is seems in inductive si…
-
It seems in GNN(graph neural network), in transductive situation, we input the whole graph and we mask the label of valid data and predict the label for the valid data.
But is seems in inductive si…
-
Hello,
Very interesting paper. Thank you for uploading the code. In the paper the results of applying transductive idea on MAML, Reptile and RelationNet algorithms are reported in table1 and table2…
-
Hi,
Can graphSAGE/GCMC support mini-batch training / distributed training ? Any documentations?
graphSAGE: https://github.com/dmlc/dgl/blob/master/examples/pytorch/graphsage/graphsage.py
GCM…