Is Meta-training Really Necessary for Molecular Few-Shot Learning ?

arXiv:2404.02314v1 Announce Type: new
Abstract: Few-shot learning has recently attracted significant interest in drug discovery, with a recent, fast-growing literature mostly involving convoluted meta-learning strategies. We revisit the more straightforward fine-tuning approach for molecular data, and propose a regularized quadratic-probe loss based on the the Mahalanobis distance. We design a dedicated block-coordinate descent optimizer, which avoid the degenerate solutions of our loss. Interestingly, our simple fine-tuning approach achieves highly competitive performances in comparison to state-of-the-art methods, while being applicable to …

abstract arxiv cs.ai cs.lg data design discovery drug discovery few-shot few-shot learning fine-tuning literature loss meta meta-learning probe strategies training type