Graph Classification On Ptc
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Accuracy |
|---|---|
| unsupervised-universal-self-attention-network | 91.81% |
| unsupervised-universal-self-attention-network | 69.63% |
| towards-a-practical-k-dimensional-weisfeiler | 62.70% |
| discriminative-graph-autoencoder | 71.24% |
| wasserstein-weisfeiler-lehman-graph-kernels | 66.31% |
| dgcnn-disordered-graph-convolutional-neural | 65.43% |
| subgraph-networks-with-application-to | 65.88% |
| template-based-graph-neural-network-with | 72.4% |
| ddgk-learning-graph-representations-for-deep | 63.14% |
| 190910086 | 74.7% |
| unsupervised-inductive-whole-graph-embedding | 72.54% |
| improving-spectral-graph-convolution-for | 68.05% |
| spi-gcn-a-simple-permutation-invariant-graph | 56.41% |
| a-simple-baseline-algorithm-for-graph | 62.8% |
| graph-trees-with-attention | 59.1% |
| graph-isomorphism-unet | 85.7% |
| graph-representation-learning-via-hard-and | 63.53% |
| graph2vec-learning-distributed | 60.17% ± 6.86% |
| cell-attention-networks | 72.8% |
| cin-enhancing-topological-message-passing | 73.2% |
| capsule-neural-networks-for-graph | 69% |
| dagcn-dual-attention-graph-convolutional | 62.88% |
| segmented-graph-bert-for-graph-instance | 68.86% |
| graph-representation-learning-via-hard-and | 65.02% |
| how-powerful-are-graph-neural-networks | 64.40% |
| isonn-isomorphic-neural-network-for-graph | 59.9% |
| neighborhood-enlargement-in-graph-neural | 73.56% |
| gaussian-induced-convolution-for-graphs | 77.64% |
| infograph-unsupervised-and-semi-supervised | 61.65 |
| when-work-matters-transforming-classical | 73.24% |
| dropgnn-random-dropouts-increase-the | 66.3% |
| a-simple-yet-effective-baseline-for-non | 61.7% |
| provably-powerful-graph-networks | 66.17% |
| learning-convolutional-neural-networks-for | 60.00% |
| wasserstein-embedding-for-graph-learning | 67.5% |
| unsupervised-inductive-whole-graph-embedding | 73.56% |
| graph-representation-learning-via-hard-and | 62.94% |