Table 4 Comparison results with different optimization methods. Data in bold indicates optimal values.
From: Dynamic graph structure evolution for node classification with missing attributes
Dataset | Case | 5% | 15% | 35% | 55% | 75% |
|---|---|---|---|---|---|---|
Cora | EGS-si | 83.87 | 82.78 | 82.23 | 81.62 | 80.33 |
EGS (ours) | 84.77 | 84.57 | 84.48 | 83.95 | 82.13 | |
Pubmed | EGS-si | 78.55 | 77.85 | 76.56 | 76.03 | 75.23 |
EGS (ours) | 80.37 | 79.79 | 79.34 | 78.95 | 77.01 |
