Question about Edge Feature

[mickeyhan]

Hi, Thank you very much for your time in reading my question . newbie here sorry if I'm not making sense

if I have a bunch of directed graphs with varying number of nodes and edges, and individually I create some subgraphs and want edge feature in this case [0,3] to be concat of the edges in between its start and end and pass through a nn.Linear() layer, if the number of nodes and edges vary from cases to cases, some are five, some are ten or any number etc. how should I approach, by padding them all to the same size ? , or engineers using graphs dont do things like this ?

Thank you very much for your time in reading my question.

[rusty1s]

How about you use PyG transforms for this:

def add_edge(data):
    loop = torch.tensor([[0], [data.num_nodes - 1]])
    data.edge_index = torch.cat([data.edge_index, loop], dim=1)
    return data

dataset = Dataset(…, transform=add_edge)

[mickeyhan]

Thank you very much for your reply ! Have a great day !