Output embedding size does not match the input

[iacopogentile]

Hi,

I ran the following code:

print(nx.info(H))

>>>Graph with 18640 nodes and 31096080 edges

import SpectralEmbeddings.GraphAutoencoder as graph_ae

alpha = 1e-4
beta = 1e-5
hidden_dims = [128,64]  # Example dimensions
epochs = 1000
ae = graph_ae.AutoEncoder(H, alpha, beta, hidden_dims, epochs)
ae.model()
embeddings = ae.get_embeddings()
len(embeddings)
>>> 37280

Maybe I am interpreting the output improperly, but I would expect embeddings to have as many elements as the number of nodes in the graph.

Best,

IG