| Paper | Code | Accuracy | Micro F1 | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks | ✓ Link | 84.2 | DSGCN | 2020-03-26 | |
| GraphMAE: Self-Supervised Masked Graph Autoencoders | ✓ Link | 84.2 | Self-supervised GraphMAE | 2022-05-22 | |
| Learning Discrete Structures for Graph Neural Networks | ✓ Link | 84.1 | LDS-GNN | 2019-03-28 | |
| Every Node Counts: Self-Ensembling Graph Convolutional Networks for Semi-Supervised Learning | ✓ Link | 83.5 ± 0.4 | SEGCN | 2018-09-26 | |
| TREE-G: Decision Trees Contesting Graph Neural Networks | ✓ Link | 83.5 | TREE-G | 2022-07-06 | |
| Simple Spectral Graph Convolution | ✓ Link | 83.0 | SSGC | 2021-01-01 | |
| Scale Invariance of Graph Neural Networks | ✓ Link | 82.3±1.1 | ScaleNet | 2024-11-28 | |
| Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning | ✓ Link | 81.7 ± 1.5 | Graph InfoClust (GIC) | 2020-09-15 | |
| Graph Representation Learning Beyond Node and Homophily | ✓ Link | 75.12 | PairE | 2022-03-03 |