Based on your example, your unseen new graphs don’t have edges of edge type
link3. However, they do have edges of edge type
link2. I assume edges of
link2 participate in message passing during training. In that case, you can still apply the trained model.
As you said, you can score each pair of nodes after the RGCN computes the node representations and take node pairs that exceed a score threshold. You will need to determine the threshold based on a held-out validation set. In other words, use a set of graphs with edges of type
link3 unseen during training as the validation set to determine the threshold.