How does the GraphRNN-S deal with variable length?

[Brando Miranda]

I was wondering if you just set the output to make possible edges for the current graph? My guess that is the case based on:

graph-generation/main.py

Line 124 in 3444b8a

 output = MLP_plain(h_size=args.hidden_size_rnn, embedding_size=args.embedding_size_output, y_size=args.max_prev_node).cuda() 

can anyone confirm?