JuliaGraphs / JuliaGraphs/GraphNeuralNetworks.jl
GPSConv
Nobody has claimed this yet.
- Dominant language
- Julia
- Stars
- 308
- Forks
- 74
- Avg merge
- 3d 6h
- Merged PRs (30d)
- 2
Description
Would be fun to have the GPSConv layer in here and I'd be happy to take a crack at it (if deemed useful).
Should be straight forward, except the "global attention" part. Not sure if there is already an implementation somewhere to just add as a dependency (NeuralAttentionlib?) or if implementing it here directly would be the way to go. any thoughts?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the GPSConv paper and the linked PyTorch Geometric GPSConv documentation to define the layer’s expected behavior. Investigate whether NeuralAttentionlib.jl can provide the global-attention component or whether it belongs in this project. Done means GPSConv is implemented with a settled attention approach and usable behavior matching the referenced design.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100