Graph Classification On Imdb B
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| accurate-learning-of-graph-representations-1 | 73.48% |
| dropgnn-random-dropouts-increase-the | 75.7% |
| fine-tuning-graph-neural-networks-by | - |
| weisfeiler-and-leman-go-neural-higher-order | 74.2% |
| masked-attention-is-all-you-need-for-graphs | 86.250±0.957 |
| subgraph-networks-with-application-to | 75.70% |
| pure-transformers-are-powerful-graph-learners | 80.250±3.304 |
| graph-isomorphism-unet | 76% |
| learning-metrics-for-persistence-based-2 | 75.4% |
| deep-graph-kernels | 66.96% |
| how-powerful-are-graph-neural-networks | 75.1% |
| recipe-for-a-general-powerful-scalable-graph | 79.250±3.096 |
| segmented-graph-bert-for-graph-instance | 77.2% |
| unsupervised-universal-self-attention-network | 77.04% |
| when-work-matters-transforming-classical | 79.90% |
| provably-powerful-graph-networks | 72.6% |
| graph-capsule-convolutional-neural-networks | 71.69% |
| anonymous-walk-embeddings | 74.45% |
| a-fair-comparison-of-graph-neural-networks-1 | 68.8% |
| an-end-to-end-deep-learning-architecture-for | 51.69% |
| do-transformers-really-perform-bad-for-graph | 77.500±2.646 |
| an-end-to-end-deep-learning-architecture-for | 70.03% |
| dissecting-graph-neural-networks-on-graph | 73.00% |
| how-powerful-are-graph-neural-networks | 81.250±3.775 |
| spi-gcn-a-simple-permutation-invariant-graph | 60.40% |
| graph-level-representation-learning-with | 73.68% |
| weisfeiler-and-leman-go-neural-higher-order | 73.5% |
| how-attentive-are-graph-attention-networks | 80.000±2.739 |
| principal-neighbourhood-aggregation-for-graph | 78.000±3.808 |
| wasserstein-embedding-for-graph-learning | 75.4% |
| a-novel-higher-order-weisfeiler-lehman-graph | 72.2 |
| graph-attention-networks | 84.250±2.062 |
| template-based-graph-neural-network-with | 78.3% |
| semi-supervised-classification-with-graph | 79.500±3.109 |
| towards-a-practical-k-dimensional-weisfeiler | 73.4% |
| online-graph-dictionary-learning | 72.06% |
| 190910086 | 78.70% |
| unsupervised-universal-self-attention-network | 96.41% |
| graph-classification-with-2d-convolutional | 70.40% |
| generalizing-topological-graph-neural | 76.6% |
| learning-convolutional-neural-networks-for | 71.00% |
| neighborhood-enlargement-in-graph-neural | 77.94% |
| rep-the-set-neural-networks-for-learning-set | 71.46% |
| factorizable-graph-convolutional-networks | 75.3% |
| maximum-entropy-weighted-independent-set | 82.13% |
| fast-graph-representation-learning-with | 72.8% |
| infograph-unsupervised-and-semi-supervised | 73.03% |
| dissecting-graph-neural-networks-on-graph | 73.00% |
| capsule-graph-neural-network | 73.10% |
| graph-trees-with-attention | 73% |