Hypergraph Node Classification on House 0.6 (test)
73.14AccuracyHyperGCL (A6: proposed generative augmentation)
Evaluation results
| Method | Links | |
|---|---|---|
| HyperGCL (A6: proposed generative augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 73.14 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 69.88 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 69.59 | |
| SetGNNAttack Type=Net, Training Ratio=10%2022.10 | 68.88 | |
| HyperGCL (A4: feature perturbation)Attack Type=Net, Training Ratio=10%2022.10 | 68.85 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 68.84 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 67.71 | |
| HyperGCL (A4: feature perturbation)Attack Type=Random, Training Ratio=10%2022.10 | 67.55 | |
| SetGNNAttack Type=Random, Training Ratio=10%2022.10 | 67.16 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 65.23 | |
| HyperGCL (A4: feature perturbation)Attack Type=Minmax, Training Ratio=10%2022.10 | 64.97 | |
| SetGNNAttack Type=Minmax, Training Ratio=10%2022.10 | 64.78 |