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

Experimental results are lower than those reported in the paper? #2

Open
xi0927 opened this issue Oct 12, 2022 · 0 comments
Open

Experimental results are lower than those reported in the paper? #2

xi0927 opened this issue Oct 12, 2022 · 0 comments

Comments

@xi0927
Copy link

xi0927 commented Oct 12, 2022 •
edited
Loading

Based on the given codes, datasets and parameter settings (files in /scripts), I can't obtain similar results reported in the paper SUBLIME. The specific values of my attempts are shown in this figure, where most of them, especially those on node clustering, are much lower than the values reported in SUBLIME.
The CUDA version is 11.1 and all python packages needed in SUBLIME are the same versions mentioned in README.
I would like to ask whether there exist some differences between the codes and the method in paper? Do I miss some important Steps?
image
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
1 participant
@xi0927