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 | 29 | 6.65% |
Graph Learning | 22 | 5.05% |
Graph Representation Learning | 20 | 4.59% |
Graph Regression | 17 | 3.90% |
Graph Classification | 16 | 3.67% |
Graph Neural Network | 15 | 3.44% |
Link Prediction | 14 | 3.21% |
Property Prediction | 10 | 2.29% |
Graph Generation | 9 | 2.06% |