-
Notifications
You must be signed in to change notification settings - Fork 95
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Why I get the 0.94 in hop2, 0.972 in hop1, 0.48 in hop3 (metaQA full KG) #28
Comments
Can you please tell the exact commands you used? |
Are you using the pretrained KG embeddings or did you retrain them? |
Yes, I retrained it by your command in #11. |
Those aren't the best hyperparameters in #11, I just wrote that command to clarify that it does work even when batch_norm is set to 0. Please set batch_norm=1, and if possible, please let me know the MRR you get when training full MetaQA KG embedding. It should be very close to 1.0, if not 1.0 . |
Also, as mentioned in #15, we need relation scoring module for 3-hop SOTA performance. Without it we get ~0.75 test accuracy |
if set batch_norm=1, #11 is the best hyperparameters ? |
Let me confirm, please wait 15-20 minutes |
@ToneLi Yes, please try same command with batch_norm = 1. As explained in #11, this is needed because of the implementation of KG embedding done by https://github.com/ibalazevic/TuckER from which this code has been taken |
Closing this for now, please reopen if issue remains @ToneLi |
I train KG embedding again, but I still cannot get 0.49 in metaQA-full KG-3hops, do you have any advice to get 0.75 you mentioned? |
Dear authors,
Why I get the 0.94 in hop2, 0.972 in hop1, 0.48 in hop3 (metaQA full KG), I used your code, same parameters, there is a big gap with the description in your paper, what should I do?
The text was updated successfully, but these errors were encountered: