| Paper | Code | Accuracy | ModelName | ReleaseDate |
|---|---|---|---|---|
| Simple and Deep Graph Convolutional Networks | ✓ Link | 88.49% | GCNII | 2020-07-04 |
| DropEdge: Towards Deep Graph Convolutional Networks on Node Classification | ✓ Link | 88.2% | IncepGCN+DropEdge | 2019-07-25 |
| FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping | ✓ Link | 87.7867% | FDGATII | 2021-10-21 |
| Adaptive Sampling Towards Fast Graph Representation Learning | ✓ Link | 87.44±0.0034% | ASGCN | 2018-09-14 |
| Beyond Homophily with Graph Echo State Networks | 86.0±1.0 | Graph ESN | 2022-10-27 | |
| FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling | ✓ Link | 85.00% | FastGCN | 2018-01-30 |
| Inductive Representation Learning on Large Graphs | ✓ Link | 82.2% | GraphSAGE | 2017-06-07 |
| Clarify Confused Nodes via Separated Learning | ✓ Link | 73.42 ± 0.58% | NCGCN | 2023-06-04 |
| GraphMix: Improved Training of GNNs for Semi-Supervised Learning | ✓ Link | 61.8% | GraphMix (GCN) | 2019-09-25 |