Node Classification 벤치마크
Node Classification on DBLP
Accuracy
- 2020-06-07 — GRACE: Accuracy 84.2
| Rank | Model | Accuracy | Micro F1 | Inference Time (ms) | Macro F1 | Paper | Code | Year |
|---|---|---|---|---|---|---|---|---|
| 1 | GRACE | 84.2 ± 0.1 | – | – | – | Deep Graph Contrastive Representation Learning | dmlc/dgl · CRIPAC-DIG/GRACE · ycremar/DIG-SSL | 2020 |
| 2 | RR-GCN-PPV | 70.61 | – | – | – | R-GCN: The R Could Stand for Random | predict-idlab/RR-GCN | 2022 |
| 3 | R-GCN | 68.51 | – | – | – | R-GCN: The R Could Stand for Random | predict-idlab/RR-GCN | 2022 |
| 4 | DAOR | – | 87.86 | – | 87.64 | Bridging the Gap between Community and Node Representations: Graph Embedding via Community Detection | eXascaleInfolab/daor | 2019 |
| 5 | PairE | – | 80.58 | – | – | Graph Representation Learning Beyond Node and Homophily | syvail/PairE-Graph-Representation-Learning-Beyond-Node-and-Homophily | 2022 |
| 6 | FIT-GNN | – | – | 0.0018 | – | FIT-GNN: Faster Inference Time for GNNs Using Coarsening | Roy-Shubhajit/FIT-GNN | 2024 |