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 | 6.92% |
Graph Learning | 20 | 5.13% |
Graph Representation Learning | 19 | 4.87% |
Graph Classification | 15 | 3.85% |
Graph Regression | 14 | 3.59% |
Link Prediction | 13 | 3.33% |
Property Prediction | 10 | 2.56% |
Molecular Property Prediction | 9 | 2.31% |
Drug Discovery | 9 | 2.31% |