-
The nostr-filter seems to be having issues communicating with strfry if I'm understanding this correctly. Getting `Error: connect ECONNREFUSED 127.0.0.1:7777` in the nf.log when it first starts. In my…
-
Dear Daniele,
I have a num_node x num_feature matrix (node features) and a num_node x num_node matrix (graph).
To train a GNN, I used the same approach as in the example : citation_gcn.py
I th…
-
**Is your feature request related to a problem? Please describe.**
I am trying to perform node classification on multiple hypergraph , let's say I have multiple hypergraphs **80%** for training and I…
-
Hi and thanks for sharing your code.
When applying GIN to node classification task for example on cora dataset, the accuracy is low.
You said in the paper that for mean aggregation and linear functi…
-
Hi @urielsinger , thanks for the paper and the code.
I am trying to run it for a node classification task for a custom graph and get KeyError: 'label'
Looks like while initializing the model, it …
-
### 🐛 Describe the bug
After installing pyg (with pip) I ran the tests and got a lot of errors, all from the module
test/explain/algorithmtest_graphic_explainer.py
running pytest
```
=====…
-
[Nrgnn: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs](https://dl.acm.org/doi/abs/10.1145/3447548.3467364)
```bib
@inproceedings{dai2021nrgnn,
title…
-
Hi, I am running HGCN on Airport (with the command below) in the node classification task. Sadly, I received ~77.86 accuracy on test set, far below ~90.6 reported in the paper.
"python train.py --…
-
Transductive learning is very common, e.g., node classification on Cora, Citeseer, and Pubmed. I intend to analyze the GNN models, e.g., 2-layer GCN, in the NTK regime.
As I have utilize `neural_ta…
-
Hi, Hongyang, thanks for sharing the code.
Since the code for transductive tasks is not available, could you please share the hyper-parameters such as num of hidden layers in the Graph U-Net and opt…