Node Classification on ACM (Accuracy)
96.23AccuracyNone
Evaluation results
| Method | Links | |
|---|---|---|
| NoneBackbone=Graph Transformer2025.02 | 96.23 | |
| Static Noise AdditionBackbone=Graph Transformer, sigma=0.052025.02 | 95.37 | |
| ADAGEBackbone=Graph Transformer2025.02 | 94.42 | |
| CoEBackbone=GCN, Learning Paradigm=Proposed Graph-MoE2025.05 | 94.21 | |
| InfoMGFBackbone=GCN, Learning Paradigm=Unsupervised multiplex2025.05 | 92.81 | |
| GTN2026.03 | 92.68 | |
| GAT2026.03 | 92.33 | |
| IDGLBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 92.33 | |
| GTN-GP2026.03 | 92.19 | |
| ProGNNBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 92.09 | |
| GRCNBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 92 | |
| SUBLIMEBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 91.81 | |
| GCN2026.03 | 91.6 | |
| HDMIBackbone=GCN, Learning Paradigm=Unsupervised multiplex2025.05 | 91.45 | |
| GSRBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 91.39 | |
| HANBackbone=GCN, Learning Paradigm=Supervised structure-fixed GNN2025.05 | 91.3 | |
| HAN2026.03 | 90.96 | |
| GENBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 90.82 | |
| NodeFormerBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 90.73 | |
| GMoEBackbone=GCN, Learning Paradigm=Graph-MoE2025.05 | 90.29 | |
| NoneBackbone=GraphSAGE2025.02 | 90.15 | |
| pGNNAttack Type=Metattack, Perturb Ratio=20%2022.05 | 89.92 | |
| NoneBackbone=GAT2025.02 | 89.92 | |
| EvenNetAttack Type=MinMax attack, Perturbation Ratio=20%2022.05 | 89.8 | |
| EvenNetAttack Type=Metattack, Perturb Ratio=20%2022.05 | 89.78 | |
| ADAGEBackbone=GraphSAGE2025.02 | 89.74 | |
| Static Noise AdditionBackbone=GraphSAGE, sigma=0.052025.02 | 89.42 | |
| EvenNetPerturb Ratio=0.42022.05 | 89.24 | |
| STABLEBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 89.18 | |
| Static Noise AdditionBackbone=GAT, sigma=0.052025.02 | 89.07 | |
| GCNBackbone=GCN, Learning Paradigm=Supervised structure-fixed GNN2025.05 | 89.04 | |
| pGNNAttack Type=MinMax attack, Perturbation Ratio=20%2022.05 | 88.96 | |
| GPRGNNAttack Type=Metattack, Perturb Ratio=20%2022.05 | 88.79 | |
| ADAGEBackbone=GAT2025.02 | 88.69 | |
| EvenNetPerturb Ratio=1.22022.05 | 88.67 | |
| LDSBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 88.55 | |
| EvenNetPerturb Ratio=0.82022.05 | 88.26 | |
| GPRGNNAttack Type=MinMax attack, Perturbation Ratio=20%2022.05 | 88.24 | |
| BernNetAttack Type=Metattack, Perturb Ratio=20%2022.05 | 87.82 | |
| BernNetAttack Type=MinMax attack, Perturbation Ratio=20%2022.05 | 87.79 | |
| LEDF-GCN2026.04 | 87.5 | |
| NoneBackbone=GIN2025.02 | 87.32 | |
| Static Noise AdditionBackbone=GIN, sigma=0.052025.02 | 86.82 | |
| pGNNPerturb Ratio=0.42022.05 | 86.67 | |
| BernNetPerturb Ratio=0.42022.05 | 86.37 | |
| MowstBackbone=GCN, Learning Paradigm=Graph-MoE2025.05 | 85.69 | |
| pGNNPerturb Ratio=0.82022.05 | 84.55 | |
| ADAGEBackbone=GIN2025.02 | 84.24 | |
| BernNetPerturb Ratio=0.82022.05 | 82.79 | |
| GCNII2026.04 | 82.3 | |
| NDLS2026.04 | 82.2 | |
| GCN2026.04 | 82.1 | |
| BernNetPerturb Ratio=1.22022.05 | 81.9 | |
| pGNNPerturb Ratio=1.22022.05 | 81.62 | |
| GPRGNNPerturb Ratio=0.42022.05 | 79.31 | |
| JKNet-Mean2026.04 | 76.5 | |
| H2GCN2026.04 | 73.7 | |
| GPRGNNPerturb Ratio=0.82022.05 | 73.21 | |
| GPRGNNPerturb Ratio=1.22022.05 | 63.41 | |
| Static Noise AdditionBackbone=Graph Transformer, sigma=52025.02 | 42.74 | |
| Static Noise AdditionBackbone=GAT, sigma=52025.02 | 37.01 | |
| Static Noise AdditionBackbone=GIN, sigma=52025.02 | 35.92 | |
| Static Noise AdditionBackbone=GraphSAGE, sigma=52025.02 | 35.15 |