Vision Language Model is NOT All You Need: Augmentation Strategies for Molecule Language Models
This work addresses challenges in molecule-text understanding for drug discovery, but it is incremental as it builds on existing MoLM approaches with specific augmentation strategies.
The paper tackled the problem of limited molecule-text paired data and missing expertise in molecule language models (MoLM) by proposing AMOLE, which augments data with structural similarity preserving loss and transfers expertise between molecules, resulting in superior performance on various downstream tasks for drug discovery applications.
Recently, there has been a growing interest among researchers in understanding molecules and their textual descriptions through molecule language models (MoLM). However, despite some early promising developments, the advancement of MoLM still trails significantly behind that of vision language models (VLM). This is because unique challenges exist apart from VLM in the field of MoLM due to 1) a limited amount of molecule-text paired data and 2) missing expertise that occurred due to the specialized areas of focus among the experts. To this end, we propose AMOLE, which 1) augments molecule-text pairs with structural similarity preserving loss, and 2) transfers the expertise between the molecules. Specifically, AMOLE enriches molecule-text pairs by sharing descriptions among structurally similar molecules with a novel structural similarity preserving loss. Moreover, we propose an expertise reconstruction loss to transfer knowledge from molecules that have extensive expertise to those with less expertise. Extensive experiments on various downstream tasks demonstrate the superiority of AMOLE in comprehending molecules and their descriptions, highlighting its potential for application in real-world drug discovery. The source code for AMOLE is available at https://github.com/Namkyeong/AMOLE.