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

FIX: fix the bug in negative sampling. #1876

Merged
merged 1 commit into from
Sep 23, 2023

Conversation

zhengbw0324
Copy link
Collaborator

No description provided.

@zhengbw0324 zhengbw0324 merged commit 4d7822f into RUCAIBox:master Sep 23, 2023
2 checks passed
@@ -137,7 +137,7 @@ def _set_neg_sample_args(self, config, dataset, dl_format, neg_sample_args):
self.times = 1
if (
self.neg_sample_args["distribution"] == "uniform"
or "popularity"
or self.neg_sample_args["distribution"] == "popularity"
and self.neg_sample_args["sample_num"] != "none"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi @zhengbw0324,

This fix is still incorrect. When distribution is uniform, the if condition always returns True no matter what sample_num is.

So I suggest using the method mentioned in the PR:#1863.
Or you can put the self.neg_sample_args["distribution"] == "uniform" or self.neg_sample_args["distribution"] == "popularity" into a parenthesis, i.e.,

if (
      ( self.neg_sample_args["distribution"] == "uniform" 
        or self.neg_sample_args["distribution"] == "popularity" )     # <- like this
        and self.neg_sample_args["sample_num"] != "none"
):
    ...

Thanks!

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

Successfully merging this pull request may close these issues.

2 participants