You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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
The text was updated successfully, but these errors were encountered:
🚀 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:
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
The text was updated successfully, but these errors were encountered: