Hypergraph Node Classification on Cora (test)
72.15AccuracyHyperGCL (A6: proposed generative augmentation)
Evaluation results
| Method | Links | |
|---|---|---|
| HyperGCL (A6: proposed generative augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 72.15 | |
| HyperGCL (A4: feature perturbation)Attack Type=Random, Training Ratio=10%2022.10 | 72.11 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 71.98 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 71.94 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 71.9 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 71.16 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 70.86 | |
| HyperGCL (A4: feature perturbation)Attack Type=Minmax, Training Ratio=10%2022.10 | 70.52 | |
| HyperGCL (A4: feature perturbation)Attack Type=Net, Training Ratio=10%2022.10 | 70.49 | |
| SetGNNAttack Type=Random, Training Ratio=10%2022.10 | 66.87 | |
| SetGNNAttack Type=Minmax, Training Ratio=10%2022.10 | 66.58 | |
| SetGNNAttack Type=Net, Training Ratio=10%2022.10 | 66.26 |