Graph Clustering On Citeseer
Métriques
ACC
ARI
NMI
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | ACC | ARI | NMI | Paper Title | Repository |
|---|---|---|---|---|---|
| R-GMM-VGAE | 68.9 | 43.9 | 42.0 | Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering | |
| GAE | 40.8 | - | - | Variational Graph Auto-Encoders | |
| ARVGE | 54.4 | 24.5 | 26.1 | Adversarially Regularized Graph Autoencoder for Graph Embedding | |
| AGC | 67.0 | - | 41.13 | Attributed Graph Clustering via Adaptive Graph Convolution | |
| RWR-GAE | 61.6 | - | 35.4 | RWR-GAE: Random Walk Regularization for Graph Auto Encoders | |
| DAEGC+GSCAN† | - | 38.2 | 39.9 | GSCAN: Graph Stability Clustering for Applications With Noise Using Edge-Aware Excess-of-Mass | |
| ARGE | 57.3 | 34.1 | 0.35 | Adversarially Regularized Graph Autoencoder for Graph Embedding | |
| R-DGAE | 70.5 | 47.1 | 45.0 | Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering | |
| RWR-VGAE | 61.3 | - | 33.8 | RWR-GAE: Random Walk Regularization for Graph Auto Encoders |
0 of 9 row(s) selected.