Graph Classification On Mutag
Métriques
Accuracy
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy |
|---|---|
| diffwire-inductive-graph-rewiring-via-the | 86.9% |
| graph-classification-with-recurrent | 86.3% |
| online-graph-dictionary-learning | 87.09% |
| how-powerful-are-graph-neural-networks | 89.4% |
| learning-metrics-for-persistence-based-2 | 87.5% |
| optimal-transport-for-structured-data-with | 86.42% |
| rep-the-set-neural-networks-for-learning-set | 86.33% |
| isonn-isomorphic-neural-network-for-graph | 83.3% |
| hierarchical-representation-learning-in-graph | 84.7% |
| learning-convolutional-neural-networks-for | 92.63% |
| graph-kernels-based-on-linear-patterns | 88.47% |
| spi-gcn-a-simple-permutation-invariant-graph | 84.40% |
| an-end-to-end-deep-learning-architecture-for | 85.83% |
| a-persistent-weisfeilerlehman-procedure-for | - |
| edgnn-a-simple-and-powerful-gnn-for-directed | 88.8% |
| graph-representation-learning-via-hard-and | 90.00% |
| diffwire-inductive-graph-rewiring-via-the | 87.58% |
| unsupervised-universal-self-attention-network | 88.47% |
| panda-expanded-width-aware-message-passing | 88.2% |
| weisfeiler-and-leman-go-neural-higher-order | 86.1% |
| evolution-of-graph-classifiers | 100.00% |
| graph-trees-with-attention | 91.1% |
| anonymous-walk-embeddings | 87.87% |
| when-work-matters-transforming-classical | 95.00% |
| cin-enhancing-topological-message-passing | 94.4% |
| propagation-kernels-efficient-graph-kernels | 84.5% |
| weisfeiler-and-leman-go-neural-higher-order | 87.7% |
| optimal-transport-for-structured-data-with | 88.42% |
| dynamic-edge-conditioned-filters-in | 88.33% |
| panda-expanded-width-aware-message-passing | 85.75% |
| panda-expanded-width-aware-message-passing | 90.05% |
| dissecting-graph-neural-networks-on-graph | 90.84% |
| accurate-learning-of-graph-representations-1 | 83.44% |
| diffwire-inductive-graph-rewiring-via-the | 86.9% |
| dropgnn-random-dropouts-increase-the | 90.4% |
| segmented-graph-bert-for-graph-instance | 90.85% |
| graph-level-representation-learning-with | 91.25% |
| panda-expanded-width-aware-message-passing | 88.75% |
| quantum-based-subgraph-convolutional-neural | 93.13% |
| maximum-entropy-weighted-independent-set | 96.66% |
| on-valid-optimal-assignment-kernels-and | 84.5% |
| neighborhood-enlargement-in-graph-neural | 94.14% |
| deep-graph-kernels | 87.44% |
| graph-star-net-for-generalized-multi-task-1 | 91.2% |
| a-simple-baseline-algorithm-for-graph | 88.4% |
| graph2vec-learning-distributed | 83.15% ± 9.25% |
| a-simple-yet-effective-baseline-for-non | 90.1% |
| spectral-multigraph-networks-for-discovering | 89.1% |
| relation-order-histograms-as-a-network | 88.68% |
| unsupervised-universal-self-attention-network | 89.97% |
| subgraph-networks-with-application-to | 93.68% |
| online-graph-dictionary-learning | 58.45% |
| graph-isomorphism-unet | 95.7% |
| gaussian-induced-convolution-for-graphs | 94.44% |
| dissecting-graph-neural-networks-on-graph | 89.89% |
| cell-attention-networks | 94.1% |
| factorizable-graph-convolutional-networks | 89.9% |
| graph-convolutional-networks-with | 79.5% |
| learning-convolutional-neural-networks-for | 88.95% |
| infograph-unsupervised-and-semi-supervised | 89.01% |
| wasserstein-weisfeiler-lehman-graph-kernels | 87.27% |
| capsule-graph-neural-network | 86.67% |
| wasserstein-embedding-for-graph-learning | 88.3% |
| capsule-neural-networks-for-graph | 88.9% |
| template-based-graph-neural-network-with | 96.4% |
| function-space-pooling-for-graph | 83.3% |
| provably-powerful-graph-networks | 90.55% |
| fast-graph-representation-learning-with | 85.7% |
| edgnn-a-simple-and-powerful-gnn-for-directed | 86.9% |
| dagcn-dual-attention-graph-convolutional | 87.22% |
| ddgk-learning-graph-representations-for-deep | 91.58% |
| improving-attention-mechanism-in-graph-neural | 90.44% |
| optimal-transport-for-structured-data-with | 83.26% |
| fine-tuning-graph-neural-networks-by | - |