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.

Sign up for GitHub

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

Jump to bottom

Add PNA layer. #8

Merged
merged 5 commits into from
Mar 12, 2021
Merged

Add PNA layer. #8

merged 5 commits into from
Mar 12, 2021

Conversation

mallamanis
Copy link
Contributor

No description provided.

mmjb
mmjb reviewed Feb 17, 2021
View reviewed changes
Copy link
Contributor

@mmjb mmjb left a comment

Choose a reason for hiding this comment

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

I'm not sure I understand why this isn't a subclass of MlpMessagePassingLayer (of which most code seems to be a copy) that stores the extra parameter and overrides _aggregate_messages. Am I overlooking something here?

ptgnn/neuralmodels/gnn/messagepassing/pnamessagepassing.py Outdated Show resolved Hide resolved
@mallamanis mallamanis requested a review from mmjb March 11, 2021 17:13
@mallamanis
Copy link
Contributor Author

@mmjb Based on your suggestion PNA is now "just" an aggregation function and most of the previous code has now changed.

@mallamanis mallamanis merged commit 207074d into master Mar 12, 2021
@mallamanis mallamanis deleted the dev/miallama/pna-layer branch March 12, 2021 07:55
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@mmjb mmjb mmjb approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@mallamanis @mmjb