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

pytorch_scatter could maybe be faster for features aggregation #4

Open
tchaton opened this issue Jun 12, 2019 · 3 comments
Open

pytorch_scatter could maybe be faster for features aggregation #4

tchaton opened this issue Jun 12, 2019 · 3 comments

Comments

@tchaton
Copy link

tchaton commented Jun 12, 2019

https://github.com/rusty1s/pytorch_scatter

@tchaton tchaton changed the title pytorch_scatter could maybe be faster from features aggregation pytorch_scatter could maybe be faster forfeatures aggregation Jun 12, 2019
@tchaton tchaton changed the title pytorch_scatter could maybe be faster forfeatures aggregation pytorch_scatter could maybe be faster for features aggregation Jun 12, 2019
@mys007
Copy link
Owner

mys007 commented Jul 16, 2019

Sorry for the massive delay and thanks for making me aware of this framework. It's definitely worth a try, as well as looking into https://github.com/dmlc/dgl/ for a re-implementation....

@tchaton
Copy link
Author

tchaton commented Jul 23, 2019

I think pytorch_geometric should also be an option.

@mys007
Copy link
Owner

mys007 commented Jul 23, 2019

Indeed, in fact, it seems that they've even implemented ECC themselves: https://github.com/rusty1s/pytorch_geometric/blob/master/torch_geometric/nn/conv/nn_conv.py !

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