Graph Classification On Collab
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| dissecting-graph-neural-networks-on-graph | 81.34% |
| accurate-learning-of-graph-representations-1 | 80.74% |
| when-work-matters-transforming-classical | 83.16% |
| dgcnn-disordered-graph-convolutional-neural | 68.34% |
| an-end-to-end-deep-learning-architecture-for | 73.76% |
| neighborhood-enlargement-in-graph-neural | 80.71% |
| provably-powerful-graph-networks | 81.38% |
| fast-graph-representation-learning-with | 80.6% |
| a-fair-comparison-of-graph-neural-networks-1 | 73.9% |
| panda-expanded-width-aware-message-passing | 77.8% |
| panda-expanded-width-aware-message-passing | 71.4% |
| graph-representation-learning-via-hard-and | 77.48% |
| panda-expanded-width-aware-message-passing | 68.4% |
| graph-u-nets | 77.56% |
| a-non-negative-factorization-approach-to-node | 65.0% |
| diffwire-inductive-graph-rewiring-via-the | 69.87% |
| unsupervised-universal-self-attention-network | 95.62% |
| unsupervised-universal-self-attention-network | 77.84% |
| factorizable-graph-convolutional-networks | 81.2% |
| hierarchical-representation-learning-in-graph | 79.1% |
| dissecting-graph-neural-networks-on-graph | 81.50% |
| diffwire-inductive-graph-rewiring-via-the | 64.47% |
| graphmae-self-supervised-masked-graph | 80.32% |
| graph-classification-with-2d-convolutional | 71.76% |
| segmented-graph-bert-for-graph-instance | 78.42% |
| an-end-to-end-deep-learning-architecture-for | 69.45% |
| how-powerful-are-graph-neural-networks | 80.2% |
| panda-expanded-width-aware-message-passing | 75.11% |
| diffwire-inductive-graph-rewiring-via-the | 72.24% |
| hierarchical-graph-representation-learning | 75.48% |
| 190910086 | 84.20% |
| wasserstein-embedding-for-graph-learning | 79.8% |
| diffwire-inductive-graph-rewiring-via-the | 65.89% |
| maximum-entropy-weighted-independent-set | 79.66% |
| understanding-attention-in-graph-neural | 66.97% |
| deep-graph-kernels | 73.09% |
| capsule-graph-neural-network | 79.62% |
| template-based-graph-neural-network-with | 84.3% |