Node Classification 벤치마크
Node Classification on AM
Accuracy
- 2017-03-17 — R-GCN: Accuracy 89.29
- 2022-03-04 — RR-GCN-PPV-CUT (Unimportant relations removed): Accuracy 91.31
- 2024-11-17 — BoP: Accuracy 92.41
| Rank | Model | Accuracy | Paper | Code | Year |
|---|---|---|---|---|---|
| 1 | BoP | 92.41 | From Primes to Paths: Enabling Fast Multi-Relational Graph Analysis | kbogas/PAM_BoP | 2024 |
| 2 | RR-GCN-PPV-CUT (Unimportant relations removed) | 91.31 | R-GCN: The R Could Stand for Random | predict-idlab/RR-GCN | 2022 |
| 3 | SCENE | 90.05 | SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks | schmidt-ju/scene | 2023 |
| 4 | R-GCN | 89.29 | Modeling Relational Data with Graph Convolutional Networks | dmlc/dgl · dmlc/dgl · dmlc/dgl · +24 | 2017 |
| 5 | RDF2Vec+SVM | 88.33 | RDF2Vec: RDF Graph Embeddings and Their Applications | IBCNServices/pyRDF2Vec | 2017 |
| 6 | Path Tree | 86.77 | Inducing a Decision Tree with Discriminative Paths to Classify Entities in a Knowledge Graph | IBCNServices/KGPTree | 2019 |
| 7 | RR-GCN-PPV-CUT | 84.8 | R-GCN: The R Could Stand for Random | predict-idlab/RR-GCN | 2022 |
| 8 | RR-GCN-PPV | 84.65 | R-GCN: The R Could Stand for Random | predict-idlab/RR-GCN | 2022 |