Skip to content
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 some edges in the test data couldn't be found in the original dataset? #7

Open
Rumial opened this issue Nov 23, 2022 · 3 comments

Comments

@Rumial
Copy link

Rumial commented Nov 23, 2022

I downloaded the IMDB dataset and there were three txt files called test, train and valid. I compared the test data with the original dataset (given by imdb_1_10.mat) and I found out that some links in the test data which are regared as positive links don't exist in the original dataset at all.
Do you have any ideas what happend?

@NSSSJSS
Copy link
Owner

NSSSJSS commented Nov 25, 2022

We checked the data set and did not find what you said.

@NSSSJSS
Copy link
Owner

NSSSJSS commented Nov 25, 2022

IMDB has two types of edges, so it has two adjacency matrices. I don't know if you don't have a good correspondence.

@Rumial
Copy link
Author

Rumial commented Nov 28, 2022

I did consider those two adjacency matrices. I'm wondering whether the test data I downloaded went wrong since I couldn't find it
in the data catalog right now. About IMDB, there is only imdb.mat file following the links given by Tips. Where can I get those train, test, and valid data used for link prediction in IMDB? Thank you very much!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants