Add ResGConv and res_gconv_norm #10553
Open
+476
−1
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
chloisu
requested review from
akihironitta,
rusty1s and
wsad1
as code owners
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
As part of the CS224W project, @BlakeMasters and I added ResGConv and res_gconv_norm used in Chen (2025), Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems. It's a PyG implementation of the GCNConv layer in @jiechenjiechen's PyTorch implementation of the Graph Neural Preconditioners paper called GNP.
We started from the GCN2Conv layer and gcn_norm and tried to follow these implementations. We used the new layer in a fork of GNP to implement a PyG version of the ResGCN layer implemented there. If desired, this could be included as an example application of the ResGConv layer.
We hope the layer and/or normalization can be useful for others in the future.
Thank you very much in advance.