Node Classification on Wisconsin
96.3AccuracyMC-GPB (+)
Evaluation results
| Method | Links | ||
|---|---|---|---|
| MC-GPB (+)Defense Method=MC-GPB (+), Backbone Architecture=GPR-GNN2026.06 | 96.3 | — | |
| FgGSL2025.12 | 96 | — | |
| 5-HiGCNArchitecture=5-HiGCN2024.12 | 94.99 | — | |
| SOTA2024.10 | 94.99 | — | |
| RDGNN-I2024.06 | 93.72 | — | |
| RDGNN-S2024.06 | 92.94 | — | |
| DMP†2024.06 | 92.16 | — | |
| PDE-GCNMLayers=162021.08 | 91.76 | — | |
| PDE-GCN-M2024.06 | 91.76 | — | |
| PDE-GCNHLayers=162021.08 | 91.37 | — | |
| AxelGNN2025.09 | 91.25 | — | |
| PDE-GCNDLayers=82021.08 | 90.39 | — | |
| Best-DSNN2026.03 | 90.2 | — | |
| GNSNMethod Category=New, Trials=102026.05 | 90.02 | — | |
| GNSNData splits=102026.05 | 90.02 | — | |
| Best-CSNN2026.03 | 90 | — | |
| O(d)-NSD2022.06 | 89.41 | — | |
| Sheaf2022.11 | 89.41 | — | |
| GREAD-BS2022.11 | 89.41 | — | |
| NSD†2024.06 | 89.41 | — | |
| GREAD†2024.06 | 89.41 | — | |
| BundleLegendreSDSheaf Type=Bundle, Polynomial=Legendre2025.11 | 89.41 | — | |
| O(d)-NSD2025.11 | 89.41 | — | |
| Best-SNN2026.03 | 89.41 | — | |
| Best-NLSD2026.03 | 89.41 | — | |
| GREADMethod Category=Diff. equation, Trials=102026.05 | 89.41 | — | |
| SheafData splits=102026.05 | 89.41 | — | |
| GREADData splits=102026.05 | 89.41 | — | |
| CNAArchitecture=TransformerConv2024.12 | 89.29 | — | |
| JdSNN2025.11 | 89.22 | — | |
| Best-jDSNN2026.03 | 89.22 | — | |
| Gen-NSD2022.06 | 89.21 | — | |
| Best-NSP2026.03 | 89.02 | — | |
| GRAFF†2024.06 | 88.83 | — | |
| HDP2024.05 | 88.82 | — | |
| SGOS-Expn2026.02 | 88.82 | — | |
| ISN2026.03 | 88.82 | — | |
| Conn-NSD2022.06 | 88.73 | — | |
| Conn-NSD2026.03 | 88.73 | — | |
| Diag-NSD2022.06 | 88.63 | — | |
| SADE-GCN2023.05 | 88.63 | — | |
| PCNet2025.09 | 88.63 | — | |
| MM-FGCNData splits=102026.05 | 88.5 | — | |
| FSGNNEvaluation protocol=fully-supervised, Hop count=32021.05 | 88.43 | — | |
| ACM-GCNtrials=102022.05 | 88.43 | — | |
| ACM-GCN2022.11 | 88.43 | — | |
| ACM-GCN2024.05 | 88.43 | — | |
| ACMII-GCN++2024.06 | 88.43 | — | |
| ACM-GCN2023.05 | 88.43 | — | |
| ACM-GCN+2023.05 | 88.43 | — | |
| ACM-GCN2025.09 | 88.43 | — | |
| ACM-GCNData splits=102026.05 | 88.43 | — | |
| LHS2023.12 | 88.32 | — | |
| MUSE2024.08 | 88.24 | — | |
| LRGNN2024.08 | 88.23 | — | |
| GloGNN++trials=102022.05 | 88.04 | — | |
| Ordered GNN2023.02 | 88.04 | — | |
| GREAD-FB*2022.11 | 88.04 | — | |
| GloGNN2024.05 | 88.04 | — | |
| GloGNN++2023.05 | 88.04 | — | |
| Cont DiagChebySDcontinuous-time=true2025.11 | 88.04 | — | |
| GloGNN++2025.09 | 88.04 | — | |
| Best-RiSNN2026.03 | 88.04 | — | |
| OGNN2024.08 | 88.04 | — | |
| UniG-Encoder2023.08 | 88.03 | — | |
| GloGNN++2021.10 | 88 | — | |
| GNRF2025.09 | 88 | — | |
| FSGNNEvaluation protocol=fully-supervised, Hop count=82021.05 | 87.84 | — | |
| G2†2024.06 | 87.84 | — | |
| CDEData splits=102026.05 | 87.84 | — | |
| GCON-GCN2022.11 | 87.8 | — | |
| GraphCON†2024.06 | 87.8 | — | |
| GCONData splits=102026.05 | 87.8 | — | |
| H2GCN2022.06 | 87.65 | — | |
| H2GCNtrials=102022.05 | 87.65 | — | |
| H2GCNLayers=Best across layers2021.02 | 87.65 | — | |
| H2GCNVariant=best architecture2023.02 | 87.65 | — | |
| H2GCN2022.11 | 87.65 | — | |
| GREAD-FB2022.11 | 87.65 | — | |
| H2GCN2024.06 | 87.65 | — | |
| HGCN2023.05 | 87.65 | — | |
| H2GCN2025.09 | 87.65 | — | |
| H2GCNData splits=102026.05 | 87.65 | — | |
| AxelGNNSim2025.09 | 87.63 | — | |
| GRAFF2022.11 | 87.45 | — | |
| GRAFFMethod Category=Diff. equation, Trials=102026.05 | 87.45 | — | |
| GRAFFData splits=102026.05 | 87.45 | — | |
| NLMLP2020.05 | 87.3 | — | |
| NLGNN2023.12 | 87.3 | — | |
| DiGGR2024.08 | 87.25 | — | |
| GloGNNtrials=102022.05 | 87.06 | — | |
| GloGNN2022.11 | 87.06 | — | |
| GloGNN2023.08 | 87.06 | — | |
| GloGNN2023.05 | 87.06 | — | |
| GloGNNData splits=102026.05 | 87.06 | — | |
| WRGATtrials=102022.05 | 86.98 | — | |
| WRGAT2022.11 | 86.98 | — | |
| WRGAT2024.05 | 86.98 | — | |
| WRGAT2024.06 | 86.98 | — | |
| WRGAT2023.05 | 86.98 | — |