| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.0235 | N/A | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| Global Self-Attention as a Replacement for Graph Convolution | ✓ Link | 0.0671 | 0.0683 | EGT + Triangular Attention | 2021-08-07 |
| Triplet Interaction Improves Graph Transformers: Accurate Molecular Graph Learning with Triplet Graph Transformers | ✓ Link | 0.0671 | 0.0683 | TGT-At | 2024-02-07 |
| Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+ | ✓ Link | 0.0693 | 0.0705 | Uni-Mol+ | 2023-03-16 |
| One Transformer Can Understand Both 2D & 3D Molecular Data | ✓ Link | 0.0772 | 0.0782 | Transformer-M | 2022-10-04 |
| Graph Propagation Transformer for Graph Representation Learning | ✓ Link | 0.0809 | 0.0821 | GPTrans-L | 2023-05-19 |
| Topology-Informed Graph Transformer | ✓ Link | 0.0826 | | TIGT | 2024-02-03 |
| Graph Propagation Transformer for Graph Representation Learning | ✓ Link | 0.0833 | 0.0842 | GPTrans-T | 2023-05-19 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | 0.0852 | 0.0862 | GPS | 2022-05-25 |
| Global Self-Attention as a Replacement for Graph Convolution | ✓ Link | 0.0857 | 0.0862 | EGT | 2021-08-07 |
| Graph Inductive Biases in Transformers without Message Passing | ✓ Link | 0.0859 | | GRIT | 2023-05-27 |
| Graph Convolutions Enrich the Self-Attention in Transformers! | ✓ Link | 0.0860 | | Graphormer + GFSA | 2023-12-07 |
| Do Transformers Really Perform Bad for Graph Representation? | ✓ Link | 0.0864 | - | Graphormer | 2021-06-09 |
| The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles | ✓ Link | 0.0865 | | EGT+SSA+Self-ensemble | 2023-06-02 |
| GRPE: Relative Positional Encoding for Graph Transformer | ✓ Link | 0.0867 | 0.0876 | GRPE-Large | 2022-01-30 |
| The Information Pathways Hypothesis: Transformers are Dynamic Self-Ensembles | ✓ Link | 0.0876 | | EGT+SSA | 2023-06-02 |
| Pure Transformers are Powerful Graph Learners | ✓ Link | 0.0910 | 0.0919 | TokenGT | 2022-07-06 |
| How Powerful are Graph Neural Networks? | ✓ Link | 0.1195 | 0.1218 | GIN | 2018-10-01 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 0.1379 | 0.1398 | GCN | 2016-09-09 |
| OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs | ✓ Link | 0.1753 | 0.1760 | MLP-Fingerprint | 2021-03-17 |