Node Classification on DBLP (ID/OOD/Overall Accuracy)
92.27AccuracyCoE
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| CoEBackbone=GCN, Learning Paradigm=Proposed Graph-MoE2025.05 | 92.27 | — | — | — | — | |
| SUBLIMEBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 91.49 | — | — | — | — | |
| InfoMGFBackbone=GCN, Learning Paradigm=Unsupervised multiplex2025.05 | 91.45 | — | — | — | — | |
| GENBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 91.33 | — | — | — | — | |
| GMoEBackbone=GCN, Learning Paradigm=Graph-MoE2025.05 | 91.18 | — | — | — | — | |
| GRCNBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 91.1 | — | — | — | — | |
| ProGNNBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 91.1 | — | — | — | — | |
| HDMIBackbone=GCN, Learning Paradigm=Unsupervised multiplex2025.05 | 90.14 | — | — | — | — | |
| MowstBackbone=GCN, Learning Paradigm=Graph-MoE2025.05 | 89.69 | — | — | — | — | |
| LDSBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 87.17 | — | — | — | — | |
| AdNGCL2026.05 | 86.28 | — | — | — | — | |
| NegAmp.2026.05 | 85.87 | — | — | — | — | |
| GRAM2026.05 | 84.7 | — | — | — | — | |
| COSTA2026.05 | 84.5 | — | — | — | — | |
| GRACE2026.05 | 84.2 | — | — | — | — | |
| BGRL2026.05 | 84.07 | — | — | — | — | |
| DGI2026.05 | 83.2 | — | — | — | — | |
| HANBackbone=GCN, Learning Paradigm=Supervised structure-fixed GNN2025.05 | 81.28 | — | — | — | — | |
| GCNBackbone=GCN, Learning Paradigm=Supervised structure-fixed GNN2025.05 | 80.7 | — | — | — | — | |
| NodeFormerBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 80.26 | — | — | — | — | |
| IDGLBackbone=GCN, Learning Paradigm=Supervised GSL2025.05 | 79.29 | — | — | — | — | |
| STABLEBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 79 | — | — | — | — | |
| GSRBackbone=GCN, Learning Paradigm=Unsupervised GSL2025.05 | 77.83 | — | — | — | — | |
| NodePFNModel=NodePFN, Training Source=Single pre-trained model2026.04 | 74.71 | — | — | — | — | |
| GATModel=GAT, Training Source=Target dataset2026.04 | 73.87 | — | — | — | — | |
| GCNModel=GCN, Training Source=Target dataset2026.04 | 73.02 | — | — | — | — | |
| GraphAny (Cora)Model=GraphAny, Training Source=Cora2026.04 | 71.73 | — | — | — | — | |
| GraphAny (Arxiv)Model=GraphAny, Training Source=Arxiv2026.04 | 70.9 | — | — | — | — | |
| GraphAny (Products)Model=GraphAny, Training Source=Products2026.04 | 70.62 | — | — | — | — | |
| GraphAny (Wisconsin)Model=GraphAny, Training Source=Wisconsin2026.04 | 70.13 | — | — | — | — | |
| MLPModel=MLP, Training Source=Target dataset2026.04 | 56.27 | — | — | — | — | |
| CFCbackbone=GCN2025.12 | — | 78.47 | 86.89 | 84.03 | — | |
| CFC (wo / D)denoising=false, backbone=GCN2025.12 | — | 75.37 | 88.37 | 83.96 | — | |
| CFC (wo / D/M)denoising=false, manifold_mixup=false, backbone=GCN2025.12 | — | 75.18 | 87.62 | 83.4 | — | |
| CFC (wo / M)manifold_mixup=false, backbone=GCN2025.12 | — | 76.25 | 85 | 82.03 | — | |
| G2Pxy2025.12 | — | 65.88 | 62.63 | 64.65 | — | |
| GCN_PROSER2025.12 | — | 63.01 | 68.75 | 65.18 | — | |
| GCN_sigmoid2025.12 | — | 91.54 | 0 | 56.89 | — | |
| GCN_sigmoid_ττ=true2025.12 | — | 71.11 | 61.54 | 66.31 | — | |
| GCN_softmax2025.12 | — | 91.11 | 0 | 56.62 | — | |
| GCN_softmax_ττ=true2025.12 | — | 79.15 | 45.14 | 66.28 | — | |
| GNNSafe2025.12 | — | 93.85 | 47.25 | 76.21 | — | |
| GOLD2025.12 | — | 94.05 | 43.68 | 74.98 | — | |
| GPT-4o2025.12 | — | 84.26 | 56.78 | 66.11 | — | |
| NodeSafe2025.12 | — | 94.52 | 42.5 | 74.83 | — |