Node-level Regression Uncertainty Quantification on Election
100PICPER-GNN
Evaluation results
| Method | Links | ||
|---|---|---|---|
| ER-GNN2026.05 | 100 | 6.9 | |
| BayesianNN2026.05 | 100 | 2.98 | |
| QpiGNNWidth penalty (lambda)=0.12026.05 | 100 | 0.97 | |
| QpiGNNWidth penalty (lambda)=0.52026.05 | 98 | 0.77 | |
| QpiGNNWidth penalty (lambda)=opt.2026.05 | 98 | 0.77 | |
| CF-GNNoptimized=true2026.05 | 91 | 0.94 | |
| SQR-GNN2026.05 | 89 | 0.47 | |
| RQRadj.-GNN2026.05 | 89 | 0.54 | |
| CF-GNN2026.05 | 89 | 1.08 | |
| MC Dropout2026.05 | 48 | 0.18 |