Hypergraph Node Classification on House 1.0 (test)
62.41AccuracyHyperGCL (A6: proposed generative augmentation)
Evaluation results
| Method | Links | |
|---|---|---|
| HyperGCL (A6: proposed generative augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 62.41 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 60.73 | |
| HyperGCL (A4: feature perturbation)Attack Type=Net, Training Ratio=10%2022.10 | 60.1 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 60.06 | |
| SetGNNAttack Type=Net, Training Ratio=10%2022.10 | 59.95 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 58.76 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 57.74 | |
| HyperGCL (A4: feature perturbation)Attack Type=Random, Training Ratio=10%2022.10 | 57.47 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 57 | |
| SetGNNAttack Type=Random, Training Ratio=10%2022.10 | 56.86 | |
| HyperGCL (A4: feature perturbation)Attack Type=Minmax, Training Ratio=10%2022.10 | 56.65 | |
| SetGNNAttack Type=Minmax, Training Ratio=10%2022.10 | 56.52 |