Pawel Gniewek

deg argument in DegreeScalerAggregation prevents from using w/o the training set

4

### 🚀 The feature, motivation and pitch When training a model with PNA layers, there is a need to pass `deg` tensor that sets the parameters in the `DegreeScalerAggregation` ```...

LogAUC metric

1

## 🚀 Feature Area Under ROC with log transformed FPR. ### Motivation LogAUC is similar to AUROC and is a popular and effective metric to evaluate classification models on very...

Creating a DGL graph with `create_dgl_graph` function

1

I've been looking into the code, and this [line](https://github.com/mims-harvard/TxGNN/blob/1000aac7120e0022af09a3ef93dba219e16a094b/txgnn/utils.py#L755) seems a bit puzzling (numerical experiments don't show any difference in the model's performance w/ and w/o this line). What is...