JuliaGraphs / JuliaGraphs/GraphNeuralNetworks.jl
Layers support for HeteroGraphConv
Open
Nobody has claimed this yet.
good first issue
heterographs
- Dominant language
- Julia
- Stars
- 308
- Forks
- 74
- Avg merge
- 3d 6h
- Merged PRs (30d)
- 2
Description
HeteroGraphConv are build out of standard graph conv layers which are individually applied to the different relations.
The list of layers supporting integration with HeteroGraphConv should be extended.
-
AGNNConv -
CGConv -
ChebConv -
EGNNConv -
EdgeConv -
GATConv -
GATv2Conv -
GatedGraphConv -
GCNConv| -
GINConv -
GMMConv -
GraphConv -
MEGNetConv -
NNConv -
ResGatedGraphConv -
SAGEConv -
SGConv -
TransformerConv
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 by inspecting HeteroGraphConv and the already checked convolution layers, then compare their integration with the unchecked list: AGNNConv, ChebConv, EGNNConv, GatedGraphConv, GMMConv, MEGNetConv, NNConv, and TransformerConv. Done means the remaining compatible layers are supported consistently and the relevant existing tests pass.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- julia
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 45/100