| Learning Long Range Dependencies on Graphs via Random Walks | ✓ Link | 80.027 ± 0.185 | NeuralWalker | 2024-06-05 |
| Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence | ✓ Link | 77.218 ± 0.381 | GatedGCN+ | 2025-02-13 |
| Recurrent Distance Filtering for Graph Representation Learning | ✓ Link | 76.853±0.185 | GRED | 2023-12-03 |
| Graph Inductive Biases in Transformers without Message Passing | ✓ Link | 76.468 | GRIT | 2023-05-27 |
| Enhancing Graph Transformers with Hierarchical Distance Structural Encoding | ✓ Link | 76.180±0.277 | GraphGPS + HDSE | 2023-08-22 |
| An end-to-end attention-based approach for learning on graphs | ✓ Link | 75.413±0.248 | ESA (Edge set attention, no positional encodings) | 2024-02-16 |
| Exphormer: Sparse Transformers for Graphs | ✓ Link | 74.754±0.194 | Exphormer | 2023-03-10 |
| Topology-Informed Graph Transformer | ✓ Link | 73.955 | TIGT | 2024-02-03 |
| Automatic Relation-aware Graph Network Proliferation | ✓ Link | 73.90 | ARGNP | 2022-05-31 |
| Directional Graph Networks | ✓ Link | 72.84 | DGN | 2020-10-06 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | 72.298 | GPS | 2022-05-25 |
| Principal Neighbourhood Aggregation for Graph Nets | ✓ Link | 70.47 | PNA | 2020-04-12 |
| Graph Transformers without Positional Encodings | | 70.194 | EIGENFORMER | 2024-01-31 |
| Residual Gated Graph ConvNets | ✓ Link | 69.37 | GatedGCN | 2017-11-20 |
| Global Self-Attention as a Replacement for Graph Convolution | ✓ Link | 68.702 | EGT | 2021-08-07 |
| Benchmarking Graph Neural Networks | ✓ Link | 67.312 | GatedGCN | 2020-03-02 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 66.08 | GraphSage | 2017-06-07 |
| Graph Attention Networks | ✓ Link | 65.48 | GAT | 2017-10-30 |
| Geometric deep learning on graphs and manifolds using mixture model CNNs | ✓ Link | 53.42 | MoNet | 2016-11-25 |
| How Powerful are Graph Neural Networks? | ✓ Link | 53.28 | GIN | 2018-10-01 |