Node Classification On Pokec
Metrics
Accuracy
Results
Performance results of various models on this benchmark
Model Name | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GloGNN++ | 83.05±0.07 | Finding Global Homophily in Graph Neural Networks When Meeting Heterophily | |
| GCN | 86.33 ± 0.17 | Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification | |
| Polynormer | 86.10±0.05 | Polynormer: Polynomial-Expressive Graph Transformer in Linear Time | |
| NeuralWalker | 86.46 ± 0.09 | Learning Long Range Dependencies on Graphs via Random Walks | |
| OptBasisGNN | 82.83±0.04 | Graph Neural Networks with Learnable and Optimal Polynomial Bases | |
| Dual-Net GNN | 81.55±0.09 | Feature Selection: Key to Enhance Node Classification with Graph Neural Networks | |
| LINKX | 82.04±0.07 | Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods |
0 of 7 row(s) selected.