Link Prediction On Citeseer
Metriken
AP
AUC
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | |||
|---|---|---|---|
| NESS | 99.5 | 99.43 | NESS: Node Embeddings from Static SubGraphs |
| VGNAE | 97.1 | 97 | Variational Graph Normalized Auto-Encoders |
| Graph InfoClust (GIC) | 96.8 | 97 | Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning |
| GNAE | 97 | 96.5 | Variational Graph Normalized Auto-Encoders |
| Walkpooling | 96.04 | 95.94 | Neural Link Prediction with Walk Pooling |
| BANE | - | 95.59% | Binarized Attributed Network Embedding |
| S-VGAE | 95.2 | 94.7 | Hyperspherical Variational Auto-Encoders |
| sGraphite-VAE | 95.4% | 94.1% | Graphite: Iterative Generative Modeling of Graphs |
| NBFNet | 93.6% | 92.3% | Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction |
| ARGE | 93 | 91.9 | Adversarially Regularized Graph Autoencoder for Graph Embedding |
| Node Feature Agg + Similarity Metric | 91.8% | 90.9% | Rethinking Kernel Methods for Node Representation Learning on Graphs |
| MTGAE | - | - | Multi-Task Graph Autoencoders |
| Variational graph auto-encoders | - | - | Variational Graph Auto-Encoders |
0 of 13 row(s) selected.