Graph Classification On Peptides Func
평가 지표
AP
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | AP |
|---|---|
| recurrent-distance-encoding-neural-networks | 0.7133±0.0011 |
| ckgconv-general-graph-convolution-with | 0.6952 |
| unlocking-the-potential-of-classic-gnns-for | 0.7261 ± 0.0067 |
| long-range-graph-benchmark | 0.5930±0.0023 |
| diffusing-graph-attention | 0.6651±0.0010 |
| drew-dynamically-rewired-message-passing-with | 0.7150±0.0044 |
| how-powerful-are-graph-neural-networks | 0.6043±0.0216 |
| recurrent-distance-encoding-neural-networks | 0.7085±0.0027 |
| next-level-message-passing-with-hierarchical | 0.6866±0.0038 |
| exphormer-sparse-transformers-for-graphs | 0.6527±0.0043 |
| where-did-the-gap-go-reassessing-the-long | 0.6765±0.0047 |
| masked-attention-is-all-you-need-for-graphs | 0.6863±0.0044 |
| on-the-connection-between-mpnn-and-graph | 0.6685±0.0062 |
| long-range-graph-benchmark | 0.5498±0.0079 |
| where-did-the-gap-go-reassessing-the-long | 0.6860±0.0050 |
| masked-attention-is-all-you-need-for-graphs | 0.7071±0.0015 |
| graph-transformers-without-positional | 0.6414 |
| long-range-graph-benchmark | 0.5864±0.0077 |
| long-range-graph-benchmark | 0.6326±0.0126 |
| a-generalization-of-vit-mlp-mixer-to-graphs | 0.6942±0.0075 |
| path-neural-networks-expressive-and-accurate | 0.6816±0.0026 |
| panda-expanded-width-aware-message-passing | 0.6028±0.0031 |
| molecular-fingerprints-are-strong-models-for | 0.7460 |
| where-did-the-gap-go-reassessing-the-long | 0.6621±0.0067 |
| masked-attention-is-all-you-need-for-graphs | 0.7357±0.0036 |
| learning-probabilistic-symmetrization-for-1 | 0.6575 |
| recipe-for-a-general-powerful-scalable-graph | 0.6535±0.0041 |
| long-range-graph-benchmark | 0.6069±0.0035 |
| long-range-graph-benchmark | 0.6384±0.0121 |
| a-generalization-of-vit-mlp-mixer-to-graphs | 0.6921±0.0054 |
| molecular-fingerprints-are-strong-models-for | 0.7318 |
| learning-long-range-dependencies-on-graphs | 0.7096 ± 0.0078 |
| where-did-the-gap-go-reassessing-the-long | 0.6534±0.0091 |
| simple-and-deep-graph-convolutional-networks-1 | 0.5543±0.0078 |
| graph-inductive-biases-in-transformers | 0.6988±0.0082 |
| transformers-for-capturing-multi-level-graph | 0.7156±0.0058 |
| topology-informed-graph-transformer | 0.6679 |
| multiresolution-graph-transformers-and | 0.6817±0.0064 |
| spatio-spectral-graph-neural-networks | 0.7311±0.0066 |
| long-range-graph-benchmark | 0.6439±0.0075 |
| molecular-fingerprints-are-strong-models-for | 0.7311 |
| masked-attention-is-all-you-need-for-graphs | 0.7479 |
| molecular-topological-profile-moltop-simple-1 | 0.6459 ± 0.0005 |
| cin-enhancing-topological-message-passing | 0.6569±0.0117 |