Table 4. Comparison of graph classification accuracy with graph kernel methods.
| Methods | Dataset | ||||
|---|---|---|---|---|---|
| MUTAG | PTC | NCI1 | PROTEINS | D&D | |
| SP | 87.28±0.55 | 58.24±2.44 | 73.47±0.11 | 75.07±0.54 | 78.86± 0.26 |
| GK | 81.39±1.74 | 55.65±0.46 | 62.49±0.27 | 71.39±0.31 | 74.38±0.69 |
| RW | 79.17±2.07 | 55.91±0.32 | >3 days | 59.57±0.09 | >3 days |
| WL | 84.11±1.91 | 57.97±2.49 | 84.46±0.45 | 74.68±0.49 | 78.34±0.62 |
| PK | 76.00±2.69 | 59.50±2.44 | 82.54±0.47 | 73.68±0.68 | 78.25±0.51 |
| DGK | 87.44±2.72 | 60.08±2.55 | 80.31±0.46 | 75.68±0.54 | - |
| DGCNNII (proposed) | 94.44 | 76.47±2.94 | 80.32±0.76 | 82.88±0.83 | 83.33±1.29 |