FS-Mol

The 'FS-Mol' dataset/benchmark contains molecular data used to evaluate few-shot learning approaches in drug discovery by assessing their ability to generalize across tasks with limited annotations.

Papers using FS-Mol (6)

Can Tabular In-Context Learners Generalize to Biomolecular Property Prediction?2026UniMatch: Universal Matching from Atom to Task for Few-Shot Drug Discovery2025Context-enriched molecule representations improve few-shot drug discovery2023 · 12 citesIn-Context Learning for Few-Shot Molecular Property Prediction2023 · 5 citesTwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction2024 · 1 citesContextual Representation Anchor Network to Alleviate Selection Bias in Few-Shot Drug Discovery2024