- Notifications
You must be signed in to change notification settings - Fork109
Open
Description
Hi, thanks for sharing the code!
I find that after randomly breaking the adjacency matrices, the performance of CompGCN remains unchanged (0.334, DistMult+multiplication). The codes in run.py that I have changed are as follows.
for sub, rel, obj in self.data['train']: obj = random.randint(0, self.p.num_ent) edge_index.append((sub, obj)) edge_type.append(rel)# Adding inverse edgesfor sub, rel, obj in self.data['train']: obj = random.randint(0, self.p.num_ent) edge_index.append((obj, sub)) edge_type.append(rel + self.p.num_rel)Did I have any misunderstanding about the codes?
Metadata
Metadata
Assignees
Labels
No labels