Heterogeneous Node Classification On Dblp 1
評価指標
Macro-F1 (20% training data)
Macro-F1 (60% training data)
Macro-F1 (80% training data)
Micro-F1 (20% training data)
Micro-F1 (80% training data)
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
比較表
| モデル名 | Macro-F1 (20% training data) | Macro-F1 (60% training data) | Macro-F1 (80% training data) | Micro-F1 (20% training data) | Micro-F1 (80% training data) |
|---|---|---|---|---|---|
| heterogeneous-graph-attention-network | 92.03% | 93.31% | 92.53% | 92.99% | 93.29% |
| heterogeneous-graph-attention-network | 90.97% | 91.84% | 91.73% | 91.96% | 92.55% |
| non-local-attention-learning-on-large | - | 95.95% | - | - | - |
| heterogeneous-graph-attention-network | 90.79% | 92.62% | 92.38% | 91.71% | 93.09% |
| heterogeneous-deep-graph-infomax | 90.94% | - | 91.53% | 91.75% | 92.26% |
| heterogeneous-graph-attention-network | 92.24% | 93.70% | 93.08% | 93.11% | 93.99% |
| heterogeneous-deep-graph-infomax | 89.88% | - | 91.06% | 90.62% | 91.92% |
| non-local-attention-learning-on-large | - | 95.91% | - | - | - |
| heterogeneous-graph-attention-network | 77.43% | 85.27% | 84.81% | 79.37% | 86.26% |
| non-local-attention-learning-on-large | - | 96.48% | - | - | - |
| heterogeneous-graph-attention-network | 91.17% | 92.69% | 91.80% | 92.05% | 92.69% |
| heterogeneous-graph-attention-network | 90.16% | 92.48% | 91.89% | 91.53% | 92.80% |
| heterogeneous-graph-attention-network | 91.68% | 93.70% | 92.34% | 92.69% | 93.27% |
| heterogeneous-graph-attention-network | 91.64% | 93.39% | 93.44% | 92.73% | 92.53% |