Graph Models
Graph Contrastive Coding
Introduced by Qiu et al. in GCC: Graph Contrastive Coding for Graph Neural Network Pre-TrainingGraph Contrastive Coding is a self-supervised graph neural network pre-training framework to capture the universal network topological properties across multiple networks. GCC's pre-training task is designed as subgraph instance discrimination in and across networks and leverages contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations.
Source: GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Knowledge | 1 | 11.11% |
| Anomaly Detection | 1 | 11.11% |
| Feature Engineering | 1 | 11.11% |
| General Classification | 1 | 11.11% |
| Graph Classification | 1 | 11.11% |
| Graph Learning | 1 | 11.11% |
| Graph Representation Learning | 1 | 11.11% |
| Link Prediction | 1 | 11.11% |
| Node Classification | 1 | 11.11% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
