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

Update GraphGPS example #7377

Merged
merged 9 commits into from
May 17, 2023
Merged

Conversation

kasper-piskorski
Copy link
Contributor

Addressing training problems of the GraphGPS example. It is now more aligned with the reference implementation by:

  • having a LR scheduler,
  • concatenating initial node features and PEs
  • having an extra post-GPS MLP layer.
    I plotted loss and test-MAE for the example before and after changes together with results from PNA example (same dataset) for reference.
    loss
    mae_gps
    mae_updated

@kasper-piskorski kasper-piskorski requested a review from wsad1 as a code owner May 17, 2023 11:22
Copy link
Member

@rusty1s rusty1s left a comment

Choose a reason for hiding this comment

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

Thank you!

@rusty1s rusty1s merged commit fd5c112 into pyg-team:master May 17, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants