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

Why the performance of GAT in paper is so low? #6

Open
wenhaozheng-nju opened this issue Jul 6, 2022 · 1 comment
Open

Why the performance of GAT in paper is so low? #6

wenhaozheng-nju opened this issue Jul 6, 2022 · 1 comment

Comments

@wenhaozheng-nju
Copy link

The performance of GAT in origin paper is outperform than GraphSage in PPI. Why not you compare GATv2 on PPI?

@urialon
Copy link
Contributor

urialon commented Jul 6, 2022

Hi @wenhaozheng-nju ,
Thank you for your interest in our work!

We haven't tried PPI just because GNNs' results in some papers reach close to 100%, so there might not be much room for improvement.
Thus, we looked for newer and more challenging benchmarks.

However, if you are interested in this particular dataset, it's very easy to run GATv2: take any codebase that evaluates on PPI, and change the GNN type to GATv2:
https://github.com/tech-srl/how_attentive_are_gats#using-gatv2

Best,
Uri

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

No branches or pull requests

2 participants