Node Classification On Roman Empire
Metriken
Accuracy (% )
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
| Paper Title | ||
|---|---|---|
| Polynormer | 92.55±0.37 | Polynormer: Polynomial-Expressive Graph Transformer in Linear Time |
| GraphHyperConv | 92.27±0.57 | HyperAggregation: Aggregating over Graph Edges with Hypernetworks |
| FaberNet | 92.24±0.43 | HoloNets: Spectral Convolutions do extend to Directed Graphs |
| GCN | 91.27±0.20 | Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification |
| GNNMoE(GAT-like P) | 87.29±0.60 | Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification |
| GNNMoE(SAGE-like P) | 86.00±0.45 | Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification |
| GNNMoE(GCN-like P) | 85.05±0.55 | Mixture of Experts Meets Decoupled Message Passing: Towards General and Adaptive Node Classification |
0 of 7 row(s) selected.