| Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence | ✓ Link | No | 0.8258 ± 0.0055 | 0.7815 ± 0.0043 | 5547557 | GatedGCN+ | 2025-02-13 |
| []() | | No | 0.8201 ± 0.0019 | 0.7720 ± 0.0023 | 16346166 | PAS+F2GNN | |
| []() | | No | 0.8140 ± 0.0028 | 0.7811 ± 0.0012 | 3758642 | ExpC*+bag of tricks | |
| Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence | ✓ Link | No | 0.8107 ± 0.0053 | 0.7786 ± 0.0095 | 8173605 | GIN+ | 2025-02-13 |
| Unlocking the Potential of Classic GNNs for Graph-level Tasks: Simple Architectures Meet Excellence | ✓ Link | No | 0.8077 ± 0.0041 | 0.7586 ± 0.0032 | 5549605 | GCN+ | 2025-02-13 |
| Recipe for a General, Powerful, Scalable Graph Transformer | ✓ Link | No | 0.8015 | 0.7556 ± 0.0027 | 3434533 | GPS | 2022-05-25 |
| Breaking the Expressive Bottlenecks of Graph Neural Networks | ✓ Link | No | 0.7976 ± 0.0072 | 0.7518 ± 0.0080 | 1369397 | ExpC | 2020-12-14 |
| []() | | No | 0.7828 ± 0.0024 | 0.7523 ± 0.0028 | 3717160 | PAS | |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | No | 0.7752 ± 0.0069 | 0.7484 ± 0.0052 | 2336421 | DeeperGCN+FLAG | 2020-10-19 |
| DeeperGCN: All You Need to Train Deeper GCNs | ✓ Link | No | 0.7712 ± 0.0071 | 0.7313 ± 0.0078 | 2336421 | DeeperGCN | 2020-06-13 |
| []() | | No | 0.7432 ± 0.0033 | 0.6989 ± 0.0037 | 4006704 | GC-T+MCL(6.0) | |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | No | 0.7245 ± 0.0114 | 0.6789 ± 0.0079 | 3288042 | GIN+virtual node+FLAG | 2020-10-19 |
| How Powerful are Graph Neural Networks? | ✓ Link | No | 0.7037 ± 0.0107 | 0.6678 ± 0.0105 | 3288042 | GIN+virtual node | 2018-10-01 |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | No | 0.6944 ± 0.0052 | 0.6638 ± 0.0055 | 1930537 | GCN+virtual node+FLAG | 2020-10-19 |
| Robust Optimization as Data Augmentation for Large-scale Graphs | ✓ Link | No | 0.6905 ± 0.0092 | 0.6465 ± 0.0070 | 1836942 | GIN+FLAG | 2020-10-19 |
| How Powerful are Graph Neural Networks? | ✓ Link | No | 0.6892 ± 0.0100 | 0.6562 ± 0.0107 | 1836942 | GIN | 2018-10-01 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.6857 ± 0.0061 | 0.6511 ± 0.0048 | 1930537 | GCN+virtual node | 2016-09-09 |
| Semi-Supervised Classification with Graph Convolutional Networks | ✓ Link | No | 0.6839 ± 0.0084 | 0.6497 ± 0.0034 | 479437 | GCN | 2016-09-09 |