Questions about HSN tutorial

[georg-bn]

I have a couple of questions/found bugs regarding the HSN tutorial (and hence might impact other tutorials in the simplicial domain).

1. TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 326 in 18956de

   " self.layers = layers\n",

   should be self.layers = torch.nn.ModuleList(layers), so that the parameters get properly registered.

2. TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 355 in 18956de

   " return torch.softmax(logits, dim=-1)"

   should probably not have softmax, as later binary crossentropy on logits is used:

   TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 415 in 18956de

   " loss = torch.nn.functional.binary_cross_entropy_with_logits(\n",

3. TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 120 in 18956de

   "Since our task will be node classification, we must retrieve an input signal on the nodes. The signal will have shape $n_\\text{nodes} \\times$ in_channels, where in_channels is the dimension of each cell's feature. Here, we have in_channels = channels_nodes $ = 34$. This is because the Karate dataset encodes the identity of each of the 34 nodes as a one hot encoder."

   "Here, we have in_channels = channels_nodes $ = 34$. This is because the Karate dataset encodes the identity of each of the 34 nodes as a one hot encoder." This seems to be incorrect as we get 2 dim features:

   TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 145 in 18956de

   "There are 34 nodes with features of dimension 2.\n"

   and they are eigenvectors from the graph as defined in https://github.com/pyt-team/TopoNetX/blob/4c47ec24047a7af83d5a249a79c1945e7043ceea/toponetx/datasets/graph.py#L38 .

[georg-bn]

Some more things about the training loop.

4. If as suggested above in 2., the softmax is removed, then the checks y_hat > 0.5 need to be replaced by y_hat > 0. Also for using binary_cross_entropy_with_logits it is probably most convenient to let the model output a 1D vector of logits instead of 2D as is done currently.
5. There's a crucial typo where y_pred[-len(y_train) :] should instead be y_pred[:len(y_train)] here:

   TopoModelX/tutorials/simplicial/hsn_train.ipynb

   Line 423 in ed4bd96

   " accuracy = (y_pred[-len(y_train) :] == y_train).all(dim=1).float().mean().item()\n",