Table 1.
The comparison of Mol-GDL with SOTAs on seven commonly used datasets, which contain only classification tasks on molecular properties
| Dataset | BACE | BBBP | ClinTox | SIDER | tox21 | HIV | MUV |
|---|---|---|---|---|---|---|---|
| No. molecules | 1,513 | 2,039 | 1,478 | 1,427 | 7,831 | 41,127 | 93,087 |
| No. average atoms | |||||||
| No. tasks | 1 | 1 | 2 | 27 | 12 | 1 | 17 |
| D-MPNN36 | |||||||
| AttentiveFP37 | |||||||
| 38 | |||||||
| 38 | 0.875 | ||||||
| PretrainGNN39 | |||||||
| 40 | |||||||
| 40 | |||||||
| GEM41 | |||||||
| Mol-GDL |
Note that the subindex indicates standard deviation values. For instance, the element means the number of average atoms in BACE is 65, with 19 as its standard deviation. Bolding indicates best results.