MHNfs is a few-shot method trained on FS-Mol. The trained model is applied to the benchmark by using the training data as a support set without updating any model weigths.
| Test set | Target label | Metric | Score |
|---|---|---|---|
| test | CLASS_KIT | f1 | 0.3283582089552239 |
| test | CLASS_KIT | mcc | 0.09142572184009139 |
| test | CLASS_KIT | pr_auc | 0.3764792144839684 |
| test | CLASS_KIT | roc_auc | 0.7127659574468085 |
| test | CLASS_KIT | accuracy | 0.22413793103448276 |
| test | CLASS_KIT | cohen_kappa | 0.0165787490580257 |
