Graph Classification On Imdb M
Metriken
Accuracy
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Accuracy |
|---|---|
| an-end-to-end-deep-learning-architecture-for | 47.83% |
| a-fair-comparison-of-graph-neural-networks-1 | 47.6% |
| how-powerful-are-graph-neural-networks | 52.3% |
| weisfeiler-and-leman-go-neural-higher-order | 51.5% |
| fine-tuning-graph-neural-networks-by | - |
| unsupervised-universal-self-attention-network | 89.2% |
| graph-isomorphism-unet | 54% |
| graph-level-representation-learning-with | 50.69% |
| graph-trees-with-attention | 56.4% |
| maximum-entropy-weighted-independent-set | 56.23% |
| dissecting-graph-neural-networks-on-graph | 51.20% |
| spi-gcn-a-simple-permutation-invariant-graph | 44.13% |
| an-end-to-end-deep-learning-architecture-for | 42.76% |
| unsupervised-inductive-whole-graph-embedding | 50.06% |
| weisfeiler-and-leman-go-neural-higher-order | 49.5% |
| accurate-learning-of-graph-representations-1 | 50.66% |
| when-work-matters-transforming-classical | 54.53% |
| dropgnn-random-dropouts-increase-the | 51.4% |
| segmented-graph-bert-for-graph-instance | 53.4% |
| towards-a-practical-k-dimensional-weisfeiler | 50.5% |
| online-graph-dictionary-learning | 50.64% |
| learning-metrics-for-persistence-based-2 | 49.5% |
| unsupervised-universal-self-attention-network | 53.60% |
| wasserstein-embedding-for-graph-learning | 52% |
| template-based-graph-neural-network-with | 56.8% |
| graph-representation-learning-via-hard-and | 49.06% |
| unsupervised-inductive-whole-graph-embedding | 50.97% |
| rep-the-set-neural-networks-for-learning-set | 48.92% |
| neighborhood-enlargement-in-graph-neural | 54.52% |
| capsule-graph-neural-network | 50.27% |
| deep-graph-kernels | 44.55% |
| infograph-unsupervised-and-semi-supervised | 49.69% |
| dissecting-graph-neural-networks-on-graph | 51.80% |
| provably-powerful-graph-networks | 50% |
| 190910086 | 56.10% |