Skip to content

Conversation

ckhui
Copy link

@ckhui ckhui commented Dec 17, 2020

Implements a single convolutional layer of the Principal Neighbourhood Aggregation Networks in paper
"Principal Neighbourhood Aggregation for Graph Nets" https://arxiv.org/abs/2004.05718

  • add PNA model using pytorch_geometry
  • add example
  • add test

@cenyk1230
Copy link
Member

@ckhui Good job. Have you ever reproduced the results of the PNA model on some graph classification datasets?

@ckhui
Copy link
Author

ckhui commented Dec 19, 2020

@ckhui Good job. Have you ever reproduced the results of the PNA model on some graph classification datasets?

I only tested the code with PROTEINS without any parameter tuning.

As attached is the comparison with diffpool.
Screenshot 2020-12-17 at 5 21 46 PM

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

Successfully merging this pull request may close these issues.

2 participants