dmlc / dmlc/dgl

[Roadmap] GNN models, modules and others

Open
#3,849 5 comments 0 reactions 0 assignees View on GitHub
feature request topic: GNN Utilities
Dominant language
Python
Stars
14.3k
Forks
3.1k
PR merge metrics
No merged PRs in 30d

Description

dgl.nn
- [x] Simplify RelGraphConv
- [x] NN module: HGTConv
- [x] LabelPropagation #4017
- [ ] GraphSizeNorm
- [x] SIGNDiffusion transform #3982
- [ ] TopKPooling
- [ ] GENConv
- [x] GINEConv #3934
- [ ] ARMAConv
- [ ] KGNNConv
- [x] PNAConv #3901
- [ ] CorrectAndSmooth
- [ ] GraphNorm
- [x] GATv2Conv
- [ ] HypergraphConv
- [ ] SE3 Transformer
- [ ] Radial field network
- [ ] TFN
- [ ] SchNet
- [x] EGNN Conv #3901
- [ ] MetaPath2Vec

Explainability modules:
- [x] GNNExplainer
- [ ] PGExplainer
- [ ] General solution for compatibility with Captum

Samplers
- [x] ClusterGCN
- [x] ShaDow
- [ ] FastGCN
- [x] GraphSAINT samplers/dataloaders (node, edge, random walk) #3879
- [ ] HGT sampler
- [ ] LADIES sampler
- [ ] TGAT sampler
- [ ] SEAL sampler #4291
- [ ] Causal Anonymous Walks

dgl.transforms
- [x] Randomly add/drop nodes/edges
- [x] Graph Diffusion Convolution
- [ ] Positional node encoding
- [x] RandomWalkPE, LaplacianPE #3869
- [x] Feature masking #3968
- [x] Row Feature Normalizer #3968
- [x] Fast approximation of PPR #3982
- [ ] VirtualNode
- [x] #4372

Datasets
- [x] Yelp #4099
- [x] Flickr #4099
- [x] WikiCS #4035

Model examples
- [x] Large-Scale Representation Learning on Graphs via Bootstrapping #4077
- [ ] SEAL example to reproduce OGBL result #4291
- [ ] GNNAutoScale
- [ ] SE3 Transformer
- [ ] OrbNet
- [ ] D-MPNN
- [ ] mtgnn
- [ ] gcnlstm
- [ ] Graph Matching Network
- [ ] GraphRNN: https://github.com/JiaxuanYou/graph-generation
- [ ] Graph2Seq work from #2931
- [ ] NGNN + GraphSAGE/GCN, NGNN + SEAL for OGBL #4328

Graph embedding NN modules
- [x] #4368
- [x] #4369
- [ ] #4370

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.