Localization Models
Fragmentation
Introduced by Kumar et al. in Improving Expressivity of Graph Neural Networks using LocalizationGiven a pattern $P,$ that is more complicated than the patterns, we fragment $P$ into simpler patterns such that their exact count is known. In the subgraph GNN proposed earlier, look into the subgraph of the host graph. We have seen that this technique is scalable on large graphs. Also, we have seen that subgraph GNN is more expressive and efficient than traditional GNN. So, we tried to explore the expressibility when the pattern is fragmented into smaller subpatterns.
Source: Improving Expressivity of Graph Neural Networks using LocalizationPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Semantic Segmentation | 4 | 8.16% |
| Language Modelling | 3 | 6.12% |
| Management | 3 | 6.12% |
| Federated Learning | 2 | 4.08% |
| de novo peptide sequencing | 2 | 4.08% |
| Object Detection | 2 | 4.08% |
| Large Language Model | 2 | 4.08% |
| Clustering | 2 | 4.08% |
| Recommendation Systems | 2 | 4.08% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
