Hypergraph Node Classification on ModelNet40 (test)
98.49AccuracyHND-NL
Evaluation results
| Method | Links | |
|---|---|---|
| HND-NLRank↓=12026.04 | 98.49 | |
| HND-LRank↓=22026.04 | 98.48 | |
| FrameHGNNRank↓=42026.04 | 98.41 | |
| KHGNNRank↓=42026.04 | 98.33 | |
| AllSetTransformerRank↓=62026.04 | 98.2 | |
| UniGCNIIRank↓=82026.04 | 98.07 | |
| HNHNRank↓=72026.04 | 97.84 | |
| ED-HNNRank↓=82026.04 | 97.83 | |
| HyperGINERank↓=102026.04 | 97.61 | |
| HNSDRank↓=92026.04 | 97.42 | |
| AllDeepSetsRank↓=102026.04 | 96.98 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 96.58 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 96.23 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 96.09 | |
| HyperGCL (A4: feature perturbation)Attack Type=Random, Training Ratio=10%2022.10 | 95.79 | |
| SetGNNAttack Type=Random, Training Ratio=10%2022.10 | 95.74 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 95.52 | |
| HyperGCL (A4: feature perturbation)Attack Type=Net, Training Ratio=10%2022.10 | 95.44 | |
| HGNNRank↓=122026.04 | 95.44 | |
| SetGNNAttack Type=Net, Training Ratio=10%2022.10 | 95.41 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 94.82 | |
| HCHARank↓=112026.04 | 94.48 | |
| HANRank↓=132026.04 | 94.04 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 93.64 | |
| HyperGCL (A4: feature perturbation)Attack Type=Minmax, Training Ratio=10%2022.10 | 93.35 | |
| SetGNNAttack Type=Minmax, Training Ratio=10%2022.10 | 93.33 | |
| HyperGCNRank↓=142026.04 | 75.89 |