Reprogramming Language Models for Molecular Representation Learning
This work addresses the problem of limited labeled data in molecular learning by leveraging large language models, which could benefit researchers in drug discovery and materials science.
The authors propose Representation Reprogramming via Dictionary Learning (R2DL) to repurpose large language models for molecular learning tasks. R2DL achieves performance comparable to state-of-the-art toxicity prediction models trained on domain-specific data and outperforms them in limited data scenarios.
Recent advancements in transfer learning have made it a promising approach for domain adaptation via transfer of learned representations. This is especially when relevant when alternate tasks have limited samples of well-defined and labeled data, which is common in the molecule data domain. This makes transfer learning an ideal approach to solve molecular learning tasks. While Adversarial reprogramming has proven to be a successful method to repurpose neural networks for alternate tasks, most works consider source and alternate tasks within the same domain. In this work, we propose a new algorithm, Representation Reprogramming via Dictionary Learning (R2DL), for adversarially reprogramming pretrained language models for molecular learning tasks, motivated by leveraging learned representations in massive state of the art language models. The adversarial program learns a linear transformation between a dense source model input space (language data) and a sparse target model input space (e.g., chemical and biological molecule data) using a k-SVD solver to approximate a sparse representation of the encoded data, via dictionary learning. R2DL achieves the baseline established by state of the art toxicity prediction models trained on domain-specific data and outperforms the baseline in a limited training-data setting, thereby establishing avenues for domain-agnostic transfer learning for tasks with molecule data.