Graph Models
Relational Graph Convolution Network
Introduced by Schlichtkrull et al. in Modeling Relational Data with Graph Convolutional NetworksAn RGCN, or Relational Graph Convolution Network, is a an application of the GCN framework to modeling relational data, specifically to link prediction and entity classification tasks.
See here for an in-depth explanation of RGCNs by DGL.
Source: Modeling Relational Data with Graph Convolutional Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Knowledge Graphs | 7 | 11.48% |
| Link Prediction | 5 | 8.20% |
| Node Classification | 3 | 4.92% |
| Knowledge Graph Completion | 3 | 4.92% |
| Graph Embedding | 2 | 3.28% |
| Knowledge Graph Embedding | 2 | 3.28% |
| Multi-Task Learning | 2 | 3.28% |
| General Classification | 2 | 3.28% |
| Question Answering | 2 | 3.28% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
