| Clarify Confused Nodes via Separated Learning | ✓ Link | 96.64 ± 0.29 | | NCGCN | 2023-06-04 |
| Clarify Confused Nodes via Separated Learning | ✓ Link | 96.48 ± 0.25 | | NCSAGE | 2023-06-04 |
| Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification | ✓ Link | 96.38±0.11 | | GraphSAGE | 2024-06-13 |
| Inferring from References with Differences for Semi-Supervised Node Classification on Graphs | ✓ Link | 95.99% | | 3ference | 2022-04-11 |
| Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification | ✓ Link | 95.81±0.26 | | GNNMoE(GCN-like P) | 2024-12-11 |
| Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 95.80% | | CoLinkDist | 2021-06-16 |
| Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 95.74% | | CoLinkDistMLP | 2021-06-16 |
| Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification | ✓ Link | 95.72±0.23 | | GNNMoE(GAT-like P) | 2024-12-11 |
| Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 95.68% | | LinkDistMLP | 2021-06-16 |
| Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification | ✓ Link | 95.68±0.24 | | GNNMoE(SAGE-like P) | 2024-12-11 |
| Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages | ✓ Link | 95.66% | | LinkDist | 2021-06-16 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 95.13% | | HH-GraphSAGE | 2023-08-17 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 95.11% | | GraphSAGE | 2023-08-17 |
| Exphormer: Sparse Transformers for Graphs | ✓ Link | 94.93±0.46% | | Exphormer | 2023-03-10 |
| Unifying Graph Convolutional Neural Networks and Label Propagation | ✓ Link | 94.8 ± 0.4 | | GCN-LPA | 2020-02-17 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 94.71% | | HH-GCN | 2023-08-17 |
| Half-Hop: A graph upsampling approach for slowing down message passing | ✓ Link | 94.06% | | GCN | 2023-08-17 |
| Diffusion Improves Graph Learning | ✓ Link | 93.01% | | GCN (PPR Diffusion) | 2019-10-28 |
| Towards Deeper Graph Neural Networks | ✓ Link | 92.8% | | DAGNN (Ours) | 2020-07-18 |
| SIGN: Scalable Inception Graph Neural Networks | ✓ Link | 91.98 ± 0.50 | | SIGN | 2020-04-23 |
| GraphMix: Improved Training of GNNs for Semi-Supervised Learning | ✓ Link | 91.83 ± 0.51 | | GraphMix (GCN) | 2019-09-25 |
| Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning | ✓ Link | 89.4 ± 0.4 | | Graph InfoClust (GIC) | 2020-09-15 |
| SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations | ✓ Link | 88.7% | | SNoRe | 2020-09-08 |
| FIT-GNN: Faster Inference Time for GNNs Using Coarsening | ✓ Link | | 0.0017 | FIT-GNN | 2024-10-19 |