Graph Models
GraphSAGE
Introduced by Hamilton et al. in Inductive Representation Learning on Large GraphsGraphSAGE is a general inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data.
Image from: Inductive Representation Learning on Large Graphs
Source: Inductive Representation Learning on Large Graphs
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Node Classification | 13 | 16.46% |
| Graph Classification | 8 | 10.13% |
| General Classification | 8 | 10.13% |
| Link Prediction | 6 | 7.59% |
| Graph Representation Learning | 5 | 6.33% |
| Graph Attention | 5 | 6.33% |
| Intrusion Detection | 3 | 3.80% |
| Recommendation Systems | 3 | 3.80% |
| Graph Learning | 2 | 2.53% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
