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?Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Graph Classification | 8 | 11.59% |
Node Classification | 6 | 8.70% |
Graph Neural Network | 6 | 8.70% |
Graph Learning | 3 | 4.35% |
Classification | 3 | 4.35% |
General Classification | 3 | 4.35% |
Feature Engineering | 2 | 2.90% |
Graph Representation Learning | 2 | 2.90% |
Molecular Property Prediction | 2 | 2.90% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |