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.

Sign up for GitHub

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

Jump to bottom

Some negative samples may exist in the test set, Is it reasonable to do so? #64

Open
FwtGit opened this issue Mar 16, 2020 · 2 comments
Open

Some negative samples may exist in the test set, Is it reasonable to do so? #64

FwtGit opened this issue Mar 16, 2020 · 2 comments

Comments

@FwtGit
Copy link

FwtGit commented Mar 16, 2020

In your code, you just check whether the randomly generated negative sampling exists in the training set, therefore, some negative samples may exist in the test set, Is it reasonable to do so?
@xindubawukong
Copy link

I think this is a small bug.

@Harlan1997
Copy link

Harlan1997 commented Dec 10, 2020 •
edited
Loading

I am confused too. I tried to generate training negative samples not exist in the observed data and I found that the performance was much worse than before. Why?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@xindubawukong @FwtGit @Harlan1997