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

Implementing Bag of Tricks for Node Classification with Graph Neural Networks #9831

Open
mattjhayes3 opened this issue Dec 9, 2024 · 0 comments
Labels

Comments

@mattjhayes3
Copy link

mattjhayes3 commented Dec 9, 2024

🚀 The feature, motivation and pitch

Hello PyG team,
@chriskynguyen, @liuvince, and I are CS224W students and have been working on implementing tricks from https://arxiv.org/abs/2103.13355.

We hope PyG users will find the following helpful to “level the playing field” for future research and squeeze extra performance out for production models. We’ll be linking separate pull requests for each of the tricks they discuss that are not already implemented:

  • “Label Usage”
  • GAT with Symmetric Normalized Adjacency Matrix
  • “Non-interactive” GAT
  • $\text{Log }\epsilon$ loss

We would much appreciate your consideration and review of any of these.
Additional descriptions and pull requests to come shortly.

Thank you!

Alternatives

To be discussed in individual PRs.

Additional context

No response

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

No branches or pull requests

1 participant