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 | 6.89% |
Graph Learning | 21 | 5.36% |
Graph Representation Learning | 19 | 4.85% |
Graph Classification | 15 | 3.83% |
Graph Regression | 14 | 3.57% |
Link Prediction | 13 | 3.32% |
Property Prediction | 10 | 2.55% |
Molecular Property Prediction | 9 | 2.30% |
Drug Discovery | 9 | 2.30% |