Link Prediction On Cora
평가 지표
AP
AUC
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | AP | AUC | Paper Title | Repository |
|---|---|---|---|---|
| BANE | 93.2% | 93.50% | Rethinking Kernel Methods for Node Representation Learning on Graphs | - |
| NBFNet | 96.2% | 95.6% | Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction | - |
| Graph InfoClust (GIC) | 93.3% | 93.5% | Binarized Attributed Network Embedding | |
| S-VGAE | 94.1% | 94.1% | Hyperspherical Variational Auto-Encoders | - |
| VGNAE | 95.8% | 95.4% | Variational Graph Normalized Auto-Encoders | - |
| Walkpooling | 96.0% | 95.9% | Neural Link Prediction with Walk Pooling | - |
| NESS | 98.71% | 98.46% | NESS: Node Embeddings from Static SubGraphs | - |
| GNAE | 95.7% | 95.6% | Variational Graph Normalized Auto-Encoders | - |
| ARGE | 93.2% | 92.4% | Adversarially Regularized Graph Autoencoder for Graph Embedding | - |
| Variational graph auto-encoders | - | - | Variational Graph Auto-Encoders | - |
| sGraphite-VAE | 93.5% | 93.7% | Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning | - |
| PPPNE | 93.9% | 92.5% | PPPNE: Personalized proximity preserved network embedding | - |
| MTGAE | - | - | Multi-Task Graph Autoencoders | - |
0 of 13 row(s) selected.