Node Classification on Coauthor Physics
97.54AccuracyGCN†
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GCN†Recipe=Deep2026.05 | 97.54 | — | — | |
| GCNImplementation=Ours2024.06 | 97.46 | — | — | |
| NAGphormerImplementation=Ours2024.06 | 97.35 | — | — | |
| NAGphormerImplementation=Literature2024.06 | 97.34 | — | — | |
| GAT†Recipe=Deep2026.05 | 97.34 | — | — | |
| NodeMoE2026.06 | 97.34 | — | — | |
| PolynormerImplementation=Literature2024.06 | 97.27 | — | — | |
| SAGE†Recipe=Deep2026.05 | 97.27 | — | — | |
| Polynormer2026.05 | 97.27 | — | — | |
| GATImplementation=Ours2024.06 | 97.25 | — | — | |
| ChebNetII2026.06 | 97.21 | — | — | |
| GraphSAGEImplementation=Ours2024.06 | 97.19 | — | — | |
| PolynormerImplementation=Ours2024.06 | 97.18 | — | — | |
| GraphGPSImplementation=Literature2024.06 | 97.12 | — | — | |
| GCNImplementation=Literature2024.06 | 97.12 | — | — | |
| GraphGPS2026.05 | 97.12 | — | — | |
| AGDN-HA2026.06 | 97.11 | — | — | |
| FilterMoE2026.06 | 97.1 | — | — | |
| JacobiConv2026.06 | 97.09 | — | — | |
| ExphormerImplementation=Ours2024.06 | 97.06 | — | — | |
| AGDN-HC2026.06 | 97.05 | — | — | |
| ADC2026.06 | 97.03 | — | — | |
| ACMGCN2026.06 | 96.96 | — | — | |
| NFGNN2026.06 | 96.94 | — | — | |
| ExphormerImplementation=Literature2024.06 | 96.89 | — | — | |
| GPRGNN2026.06 | 96.85 | — | — | |
| SGFormerImplementation=Ours2024.06 | 96.75 | — | — | |
| DSF2026.06 | 96.72 | — | — | |
| GraphGPSImplementation=Ours2024.06 | 96.71 | — | — | |
| OURSPipeline=A2026.05 | 96.67 | — | — | |
| SGFormerImplementation=Literature2024.06 | 96.6 | — | — | |
| SGFormer2026.05 | 96.6 | — | — | |
| Mowst2026.06 | 96.6 | — | — | |
| GMoE2026.06 | 96.52 | — | — | |
| GraphSAGEImplementation=Literature2024.06 | 96.49 | — | — | |
| GraphSAGE2026.06 | 96.49 | — | — | |
| NodeFormerImplementation=Ours2024.06 | 96.48 | — | — | |
| GOATImplementation=Ours2024.06 | 96.47 | — | — | |
| NodeFormerImplementation=Literature2024.06 | 96.45 | — | — | |
| GAMLP2026.06 | 96.25 | — | — | |
| GOATImplementation=Literature2024.06 | 96.24 | — | — | |
| GCN2026.06 | 96.18 | — | — | |
| GATImplementation=Literature2024.06 | 96.17 | — | — | |
| GAT2026.06 | 96.17 | — | — | |
| HOGA2026.06 | 95.93 | — | — | |
| SIGN2026.06 | 95.47 | — | — | |
| OKDEEMMethod Category=Stochastic GNNs, Setting=Inductive, Inference Mode=One-hop2023.05 | 94.46 | — | — | |
| GEMMethod Category=Deep GNNs, Setting=Inductive2023.05 | 94.44 | — | — | |
| OKDEEM0Method Category=MLP-based, Setting=Inductive, Inference Mode=Non-hop2023.05 | 94.11 | — | — | |
| EEMMethod Category=Stochastic GNNs, Setting=Inductive2023.05 | 94.01 | — | — | |
| GCNModel=GCN, Training Source=Target dataset2026.04 | 93.93 | — | — | |
| GCNIIMethod Category=Deep GNNs, Setting=Inductive2023.05 | 93.81 | — | — | |
| NodePFNTraining=Zero-shot from synthetic prior data2026.04 | 93.43 | — | — | |
| NodePFNModel=NodePFN, Training Source=Single pre-trained model2026.04 | 93.43 | — | — | |
| EGNNLayer Num=322021.07 | 93.3 | — | — | |
| EGNNLayer Num=162021.07 | 93.1 | — | — | |
| GATModel=GAT, Training Source=Target dataset2026.04 | 93.01 | — | — | |
| Best 2LLayers=22026.05 | 93 | — | — | |
| GCNMethod Category=Deep GNNs, Setting=Inductive2023.05 | 92.93 | — | — | |
| GCNIILayer Num=162021.07 | 92.9 | — | — | |
| GCNIILayer Num=322021.07 | 92.9 | — | — | |
| JKNetMethod Category=Deep GNNs, Setting=Inductive2023.05 | 92.87 | — | — | |
| H2GCNTraining=Dataset-specific2026.04 | 92.86 | — | — | |
| GPRGNNTraining=Dataset-specific2026.04 | 92.76 | — | — | |
| JKNetLayer Num=22021.07 | 92.7 | — | — | |
| APPNPLayer Num=162021.07 | 92.7 | — | — | |
| GraphAny (Cora)Model=GraphAny, Training Source=Cora2026.04 | 92.7 | — | — | |
| GraphAny (Arxiv)Model=GraphAny, Training Source=Arxiv2026.04 | 92.69 | — | — | |
| GraphAny (Products)Model=GraphAny, Training Source=Products2026.04 | 92.66 | — | — | |
| APPNPLayer Num=322021.07 | 92.6 | — | — | |
| EGNNLayer Num=22021.07 | 92.6 | — | — | |
| GraphAny (Wisconsin)Model=GraphAny, Training Source=Wisconsin2026.04 | 92.54 | — | — | |
| DropEdgeLayer Num=22021.07 | 92.5 | — | — | |
| GCNIILayer Num=22021.07 | 92.5 | — | — | |
| GCNLayer Num=22021.07 | 92.4 | — | — | |
| FAGCNTraining=Dataset-specific2026.04 | 92.34 | — | — | |
| APPNPLayer Num=22021.07 | 92.3 | — | — | |
| SGCLayer Num=22021.07 | 92.2 | — | — | |
| JKNetLayer Num=162021.07 | 92.2 | — | — | |
| ECNMethod Category=Stochastic GNNs, Setting=Inductive2023.05 | 91.86 | — | — | |
| SGCLayer Num=162021.07 | 91.7 | — | — | |
| JKNetLayer Num=322021.07 | 91.6 | — | — | |
| GraphMLPMethod Category=MLP-based, Setting=Inductive2023.05 | 89.32 | — | — | |
| MLPMethod Category=MLP-based, Setting=Inductive2023.05 | 87.79 | — | — | |
| MLPModel=MLP, Training Source=Target dataset2026.04 | 87.43 | — | — | |
| PairNormLayer Num=22021.07 | 86.3 | — | — | |
| DropEdgeLayer Num=162021.07 | 85.1 | — | — | |
| SGCLayer Num=322021.07 | 84.8 | — | — | |
| PairNormLayer Num=162021.07 | 84 | — | — | |
| PairNormLayer Num=322021.07 | 83.6 | — | — | |
| DropEdgeLayer Num=322021.07 | 35.2 | — | — | |
| GCNLayer Num=162021.07 | 13.5 | — | — | |
| GCNLayer Num=322021.07 | 13.1 | — | — | |
| GCNJumping Knowledge (JK) Strategy=Pool2019.04 | 0.9674 | — | — | |
| GCNJumping Knowledge (JK) Strategy=Concat2019.04 | 0.9671 | — | — | |
| GATJumping Knowledge (JK) Strategy=Concat2019.04 | 0.9666 | — | — | |
| GATJumping Knowledge (JK) Strategy=Pool2019.04 | 0.9662 | — | — | |
| DNANumber of groups (g)=82019.04 | 0.9658 | — | — | |
| GCNJumping Knowledge (JK) Strategy=LSTM2019.04 | 0.9655 | — | — | |
| DNANumber of groups (g)=162019.04 | 0.9653 | — | — |