Node Classification on Cornell
97.8AccuracyMC-GPB (+)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MC-GPB (+)Defense Method=MC-GPB (+), Backbone Architecture=GPR-GNN2026.06 | 97.8 | — | — | — | |
| FgGSL2025.12 | 94 | — | — | — | |
| RDGNN-I2024.06 | 92.72 | — | — | — | |
| SOTA2024.10 | 92.72 | — | — | — | |
| RDGNN-S2024.06 | 92.43 | — | — | — | |
| PDE-GCNMLayers=642021.08 | 89.73 | — | — | — | |
| PDE-GCN-M2024.06 | 89.73 | — | — | — | |
| GraspLLMBackbone=Vicuna-7B-v1.5, Evaluation Protocol=Zero-shot2026.06 | 89.7 | — | — | — | |
| GraspLLMBackbone=LLaMA-3.1-8B, Evaluation Protocol=Zero-shot2026.06 | 89.7 | — | — | — | |
| PDE-GCNHLayers=642021.08 | 89.45 | — | — | — | |
| PDE-GCNDLayers=22021.08 | 89.19 | — | — | — | |
| DMP†2024.06 | 89.19 | — | — | — | |
| GNSNMethod Category=New, Trials=102026.05 | 89.19 | — | — | — | |
| GNSNData splits=102026.05 | 89.19 | — | — | — | |
| KGNN2026.06 | 89.19 | — | — | — | |
| BES2026.06 | 89.19 | — | — | — | |
| MM-FGCNData splits=102026.05 | 88.9 | — | — | — | |
| GNFBC2026.03 | 88.89 | — | — | — | |
| CATv3-supBase Model=GATv32023.12 | 88.8 | — | — | — | |
| CATv3-semiBase Model=GATv32023.12 | 88.4 | — | — | — | |
| DiGGR2024.08 | 88.38 | — | — | — | |
| CATv3-unsupBase Model=GATv3, Random Seed=02023.12 | 88.2 | — | — | — | |
| CATv3-unsupBase Model=GATv3, Random Seed=1002023.12 | 88 | — | — | — | |
| FSGNNEvaluation protocol=fully-supervised, Hop count=82021.05 | 87.84 | — | — | — | |
| HDP2024.05 | 87.84 | — | — | — | |
| Best-DSNN2026.03 | 87.84 | — | — | — | |
| CATv3-unsupBase Model=GATv3, Random Seed=102023.12 | 87.5 | — | — | — | |
| G2†2024.06 | 87.3 | — | — | — | |
| Best-NLSD2026.03 | 87.3 | — | — | — | |
| GNRF2025.09 | 87.28 | — | — | — | |
| FSGNNEvaluation protocol=fully-supervised, Hop count=32021.05 | 87.03 | — | — | — | |
| Ordered GNN2023.02 | 87.03 | — | — | — | |
| GREAD-AC2022.11 | 87.03 | — | — | — | |
| GREAD†2024.06 | 87.03 | — | — | — | |
| OGNN2024.08 | 87.03 | — | — | — | |
| GREADMethod Category=Diff. equation, Trials=102026.05 | 87.03 | — | — | — | |
| GREADData splits=102026.05 | 87.03 | — | — | — | |
| AxelGNN2025.09 | 87.02 | — | — | — | |
| BundleGagenbauerSDSheaf Type=Bundle, Polynomial=Gegenbauer2025.11 | 86.76 | — | — | — | |
| Diag-NSD2022.06 | 86.49 | — | — | — | |
| GREAD-BS2022.11 | 86.49 | — | — | — | |
| GREAD-F2022.11 | 86.49 | — | — | — | |
| NSD†2024.06 | 86.49 | — | — | — | |
| ACMII-GCN++2024.06 | 86.49 | — | — | — | |
| DiagChebyT1SDSheaf Type=Diagonal, Polynomial=Chebyshev, Order=T12025.11 | 86.49 | — | — | — | |
| Best-SNN2026.03 | 86.49 | — | — | — | |
| GNFBC(w/o Lneg)negative feedback loss=excluded2026.03 | 86.48 | — | — | — | |
| LRGNN2024.08 | 86.48 | — | — | — | |
| GATv3Variant=Base2023.12 | 86.3 | — | — | — | |
| GREAD-ST2022.11 | 86.22 | — | — | — | |
| GREAD-FB2022.11 | 86.22 | — | — | — | |
| CDEData splits=102026.05 | 86.22 | — | — | — | |
| SADE-GCN2023.05 | 86.21 | — | — | — | |
| LHS2023.12 | 85.96 | — | — | — | |
| Conn-NSD2022.06 | 85.95 | — | — | — | |
| BLEND2022.02 | 85.95 | — | — | — | |
| GloGNN++trials=102022.05 | 85.95 | — | — | — | |
| MGNNI2022.10 | 85.95 | — | — | — | |
| BLEND2022.11 | 85.95 | — | — | — | |
| GREAD-FB*2022.11 | 85.95 | — | — | — | |
| GloGNN2024.05 | 85.95 | — | — | — | |
| GloGNN++2023.05 | 85.95 | — | — | — | |
| BLENDcontinuous-time=true2025.11 | 85.95 | — | — | — | |
| GloGNN++2025.09 | 85.95 | — | — | — | |
| ISN2026.03 | 85.95 | — | — | — | |
| Best-RiSNN2026.03 | 85.95 | — | — | — | |
| Conn-NSD2026.03 | 85.95 | — | — | — | |
| BLENDData splits=102026.05 | 85.95 | — | — | — | |
| GloGNN+2021.10 | 85.9 | — | — | — | |
| Gen-NSD2022.06 | 85.68 | — | — | — | |
| GGCN2022.06 | 85.68 | — | — | — | |
| GGCNtrials=102022.05 | 85.68 | — | — | — | |
| GGCNLayers=Best across layers2021.02 | 85.68 | — | — | — | |
| GGCN2023.02 | 85.68 | — | — | — | |
| GGCN2022.11 | 85.68 | — | — | — | |
| GREAD-Z2022.11 | 85.68 | — | — | — | |
| GGCN2024.05 | 85.68 | — | — | — | |
| GGCN2024.06 | 85.68 | — | — | — | |
| GGCN2023.05 | 85.68 | — | — | — | |
| ACM-GCN+2023.05 | 85.68 | — | — | — | |
| GGCN2025.09 | 85.68 | — | — | — | |
| GGCNData splits=102026.05 | 85.68 | — | — | — | |
| Best-jDSNN2026.03 | 85.41 | — | — | — | |
| ACMP2022.11 | 85.4 | — | — | — | |
| ACMP-GCN2024.06 | 85.4 | — | — | — | |
| ACMPMethod Category=Diff. equation, Trials=102026.05 | 85.4 | — | — | — | |
| ACMPData splits=102026.05 | 85.4 | — | — | — | |
| ACM-GCNtrials=102022.05 | 85.14 | — | — | — | |
| ACM-GCN2022.11 | 85.14 | — | — | — | |
| GPNN2023.12 | 85.14 | — | — | — | |
| ACM-GCN2024.05 | 85.14 | — | — | — | |
| ACM-GCN2023.05 | 85.14 | — | — | — | |
| ACM-GCN2025.09 | 85.14 | — | — | — | |
| GREET2024.08 | 85.14 | — | — | — | |
| ACM-GCNData splits=102026.05 | 85.14 | — | — | — | |
| EIGNN2022.02 | 85.13 | — | — | — | |
| EIGNN2022.10 | 85.13 | — | — | — | |
| GREET2023.12 | 85.1 | — | — | — | |
| NLMLP2020.05 | 84.9 | — | — | — | |
| NLGNN2023.12 | 84.9 | — | — | — |