This is Graph Transformer method, proposed as a generalization of Transformer Neural Network architectures, for arbitrary graphs.
Compared to the original Transformer, the highlights of the presented architecture are:
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Node Classification | 27 | 6.67% |
Graph Learning | 21 | 5.19% |
Graph Representation Learning | 19 | 4.69% |
Graph Regression | 15 | 3.70% |
Graph Classification | 15 | 3.70% |
Link Prediction | 13 | 3.21% |
Property Prediction | 10 | 2.47% |
Molecular Property Prediction | 9 | 2.22% |
Drug Discovery | 9 | 2.22% |