Hypergraph Node Classification on NTU 2012 (test)
93.32AccuracyHND-L
Evaluation results
| Method | Links | |
|---|---|---|
| HND-LRank↓=22026.04 | 93.32 | |
| HND-NLRank↓=12026.04 | 92.15 | |
| FrameHGNNRank↓=42026.04 | 89.98 | |
| KHGNNRank↓=42026.04 | 89.6 | |
| UniGCNIIRank↓=82026.04 | 89.3 | |
| HNHNRank↓=72026.04 | 89.11 | |
| AllSetTransformerRank↓=62026.04 | 88.69 | |
| ED-HNNRank↓=82026.04 | 88.67 | |
| HyperGINERank↓=102026.04 | 88.52 | |
| HNSDRank↓=92026.04 | 88.31 | |
| AllDeepSetsRank↓=102026.04 | 88.09 | |
| HGNNRank↓=122026.04 | 87.72 | |
| HCHARank↓=112026.04 | 87.48 | |
| HANRank↓=132026.04 | 83.58 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 75.06 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Random, Training Ratio=10%2022.10 | 74.5 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 74.37 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Net, Training Ratio=10%2022.10 | 73.86 | |
| SetGNNAttack Type=Random, Training Ratio=10%2022.10 | 73.84 | |
| HyperGCL (A4: feature perturbation)Attack Type=Random, Training Ratio=10%2022.10 | 73.73 | |
| HyperGCL (A4: feature perturbation)Attack Type=Net, Training Ratio=10%2022.10 | 73.72 | |
| SetGNNAttack Type=Net, Training Ratio=10%2022.10 | 73.38 | |
| HyperGCL (A6: proposed generative augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 72.09 | |
| HyperGCL (A2: generalized hyperedge augmentation)Attack Type=Minmax, Training Ratio=10%2022.10 | 71.4 | |
| HyperGCL (A4: feature perturbation)Attack Type=Minmax, Training Ratio=10%2022.10 | 71.06 | |
| SetGNNAttack Type=Minmax, Training Ratio=10%2022.10 | 70.71 | |
| HyperGCNRank↓=142026.04 | 56.36 |