Node Classification 벤치마크
Node Classification on Shanghai
Average Top-1 Accuracy
- 2025-03-12 — GraphSAGE: Average Top-1 Accuracy 60.4
- 2025-05-29 — IM-GCN: Average Top-1 Accuracy 67.8
| Rank | Model | Average Top-1 Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | IM-GCN | 67.8 ± 0.1 | Improving the Effective Receptive Field of Message-Passing Neural Networks | bgu-cs-vil/im-mpnn | 2025 |
| 2 | GraphSAGE | 60.4 ± 0.3 | Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement | leonresearch/city-networks | 2025 |
| 3 | ChebNet | 57.9 ± 1.4 | Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement | leonresearch/city-networks | 2025 |
| 4 | SGFormer | 53.5 ± 0.3 | Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement | leonresearch/city-networks | 2025 |
| 5 | GCN | 52.4 ± 0.3 | Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement | leonresearch/city-networks | 2025 |