| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.0109±0.0002 | ESA + rings + NodeRWSE + EdgeRWSE | 2024-02-16 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.0122±0.0004 | ESA + RWSE + CY2C (Edge set attention, Random Walk Structural Encoding, clique adjacency, tuned) | 2024-02-16 |
| Topology-Informed Graph Transformer | ✓ Link | 0.014 | TIGT | 2024-02-03 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.0154±0.0001 | ESA + RWSE (Edge set attention, Random Walk Structural Encoding, tuned) | 2024-02-16 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.017±0.001 | ESA + RWSE (Edge set attention, Random Walk Structural Encoding) | 2024-02-16 |
| Graph Inductive Biases in Transformers without Message Passing | ✓ Link | 0.023 | GRIT | 2023-05-27 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | 0.024±0.007 | GraphGPS | 2022-05-25 |
| Sign and Basis Invariant Networks for Spectral Graph Representation Learning | ✓ Link | 0.024±0.003 | SignNet | 2022-02-25 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 0.027±0.001 | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| Do Transformers Really Perform Bad for Graph Representation? | ✓ Link | 0.036±0.002 | Graphormer | 2021-06-09 |
| Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings | ✓ Link | 0.042±0.003 | δ-2-GNN | 2019-04-02 |
| Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings | ✓ Link | 0.045±0.006 | δ-2-LGNN | 2019-04-02 |
| Pure Transformers are Powerful Graph Learners | ✓ Link | 0.047±0.010 | TokenGT | 2022-07-06 |
| Principal Neighbourhood Aggregation for Graph Nets | ✓ Link | 0.057±0.007 | PNA | 2020-04-12 |
| How Powerful are Graph Neural Networks? | ✓ Link | 0.068±0.004 | GIN | 2018-10-01 |
| Graph Attention Networks | ✓ Link | 0.078±0.006 | GAT | 2017-10-30 |
| How Attentive are Graph Attention Networks? | ✓ Link | 0.079±0.004 | GATv2 | 2021-05-30 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 0.126±0.003 | GraphSAGE | 2017-06-07 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | 0.152±0.023 | GCN | 2016-09-09 |