Node Classification on Amazon-Ratings (test)
57.03AccuracyLINKX+LCC
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LINKX+LCC2026.06 | 57.03 | — | |
| ACMGCN2026.06 | 55.65 | — | |
| GAT2026.01 | 55.51 | — | |
| SAGE2026.01 | 55.26 | — | |
| FAFselection=best validation2026.01 | 55.09 | — | |
| POLYNORMER2024.06 | 54.81 | — | |
| Polynormer2026.02 | 54.81 | — | |
| Polynomialarchitecture_type=Graph Transformers2026.05 | 54.81 | — | |
| NeuralWalker2024.06 | 54.58 | — | |
| IM-CO-GNNAggregation=(μ, μ)2025.05 | 54.43 | — | |
| GloGNN+LCC2026.06 | 54.42 | — | |
| CO-GNNAggregation=(μ, μ)2025.05 | 54.17 | — | |
| CO-GNN2026.02 | 54.17 | — | |
| CO-GNN(μ, μ)architecture_type=MPNNs2026.05 | 54.17 | — | |
| CO-GNNModel Category=MPNNs2025.05 | 54.17 | — | |
| CO-GNNAggregator=µ, µ2025.05 | 54.17 | — | |
| GMNarchitecture_type=Graph SSMs2026.05 | 54.07 | — | |
| GMNModel Category=Graph SSMs2025.05 | 54.07 | — | |
| GMN2025.05 | 54.07 | — | |
| IM-GatedGCN2025.05 | 54.01 | — | |
| IM-GAT-sepseparated=true2025.05 | 53.97 | — | |
| GCN2026.01 | 53.86 | — | |
| GraphSAGE2026.06 | 53.7 | — | |
| LINKX2026.06 | 53.7 | — | |
| MP-SSM2026.02 | 53.65 | — | |
| MP-SSMarchitecture_type=Graph SSMs2026.05 | 53.65 | — | |
| MP-SSMModel Category=Ours2025.05 | 53.65 | — | |
| MP-SSM2025.05 | 53.65 | — | |
| DHGNNwith embedding=true2025.10 | 53.64 | 0.52 | |
| SAGEarchitecture_type=MPNNs2026.05 | 53.63 | — | |
| SAGEModel Category=MPNNs2025.05 | 53.63 | — | |
| SAGE2025.05 | 53.63 | — | |
| OrderedGNN2026.06 | 53.62 | — | |
| GCNAugmentation=MAS2026.06 | 53.54 | — | |
| GCN-MASFramework=GRAPH CASCADES2026.06 | 53.54 | — | |
| EXPHORMER2024.06 | 53.51 | — | |
| Exphormer2025.05 | 53.51 | — | |
| Exphormerarchitecture_type=Graph Transformers2026.05 | 53.51 | — | |
| ExphormerModel Category=Graph Transformers2025.05 | 53.51 | — | |
| Exphormer2025.05 | 53.51 | — | |
| GRAMAGCNarchitecture_type=Graph SSMs2026.05 | 53.48 | — | |
| S3GNNarchitecture_type=Graph SSMs2026.05 | 53.46 | — | |
| L2G-Net2026.02 | 53.41 | — | |
| St-ChebNet2026.02 | 53.15 | — | |
| IM-CO-GNNAggregation=(Σ, Σ)2025.05 | 53.11 | — | |
| GPS2024.06 | 53.1 | — | |
| GPSarchitecture_type=Graph Transformers2026.05 | 53.1 | — | |
| GPSModel Category=Graph Transformers2025.05 | 53.1 | — | |
| GPS2025.05 | 53.1 | — | |
| FSGNN2025.05 | 52.74 | — | |
| FSGNNarchitecture_type=Heterophily-Designated GNNs2026.05 | 52.74 | — | |
| FSGNNModel Category=Heterophily-Designated GNNs2025.05 | 52.74 | — | |
| FSGNN2025.05 | 52.74 | — | |
| GCNAugmentation=TAS2026.06 | 52.74 | — | |
| GAT(-SEP)2024.06 | 52.7 | — | |
| GAT-sepseparated=true2025.05 | 52.7 | — | |
| GAT-sep2025.05 | 52.7 | — | |
| DHGNN2025.10 | 52.48 | 0.5 | |
| IM-GCN2025.05 | 52.37 | — | |
| AllSetTransformer2025.10 | 52.28 | 0.67 | |
| GTseparated=true2025.05 | 52.18 | — | |
| GT-separchitecture_type=Graph Transformers2026.05 | 52.18 | — | |
| GT-sep2025.05 | 52.18 | — | |
| LCC2026.06 | 52.17 | — | |
| H2GCN+LCC2026.06 | 52.09 | — | |
| AllDeepSets2025.10 | 51.91 | 0.68 | |
| ResNet+adj2025.05 | 51.83 | — | |
| VCR2026.06 | 51.74 | — | |
| VCR2026.06 | 51.74 | — | |
| GATPE=DEG2025.05 | 51.65 | — | |
| ED-HNN2025.10 | 51.58 | 0.53 | |
| M2MGNN2026.06 | 51.56 | — | |
| CMGNN2026.06 | 51.55 | — | |
| VCRAugmentation=TAS2026.06 | 51.35 | — | |
| CO-GNNAggregation=(Σ, Σ)2025.05 | 51.28 | — | |
| CO-GNN(Σ, Σ)architecture_type=MPNNs2026.05 | 51.28 | — | |
| CO-GNNAggregator=Σ, Σ2025.05 | 51.28 | — | |
| NAGPHORMER2024.06 | 51.26 | — | |
| NAGphormerarchitecture_type=Graph Transformers2026.05 | 51.26 | — | |
| NAGphormer2025.05 | 51.26 | — | |
| GTarchitecture_type=Graph Transformers2026.05 | 51.17 | — | |
| GTModel Category=Graph Transformers2025.05 | 51.17 | — | |
| GT2025.05 | 51.17 | — | |
| IM-GAT2025.05 | 51.16 | — | |
| GCN2026.06 | 51.08 | — | |
| GCN2026.06 | 51.08 | — | |
| GPSBackbone=GAT+Performer, PE=DEG2025.05 | 51.03 | — | |
| DSHNLight2025.10 | 50.94 | 0.68 | |
| ResNet+SGC2025.05 | 50.66 | — | |
| H2GCN2026.06 | 50.32 | — | |
| SAN2026.06 | 50.28 | — | |
| GCNPE=DEG2025.05 | 50.01 | — | |
| GloGNN2026.06 | 49.94 | — | |
| GPS_GAT+PerformerPositional Encoding=RWSE2025.05 | 49.92 | — | |
| GPSBackbone=GAT+Performer, PE=RWSE2025.05 | 49.92 | — | |
| MLP-2architecture_type=MLP2026.05 | 49.55 | — | |
| MLP-22025.05 | 49.55 | — | |
| GAT2026.06 | 49.31 | — | |
| GeDi-HNN2025.10 | 49.3 | 0.52 | |
| UniGCNII2025.10 | 49.12 | 0.46 |