Graph Embeddings
Graph Isomorphism Network
Introduced by Xu et al. in How Powerful are Graph Neural Networks?Per the authors, Graph Isomorphism Network (GIN) generalizes the WL test and hence achieves maximum discriminative power among GNNs.
Source: How Powerful are Graph Neural Networks?
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Graph Classification | 6 | 12.00% |
| Node Classification | 4 | 8.00% |
| Graph Learning | 3 | 6.00% |
| Classification | 3 | 6.00% |
| General Classification | 3 | 6.00% |
| Graph Representation Learning | 2 | 4.00% |
| Molecular Property Prediction | 2 | 4.00% |
| Property Prediction | 2 | 4.00% |
| Adversarial Attack | 2 | 4.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
