CLASS: Enhancing Cross-Modal Text-Molecule Retrieval Performance and Training Efficiency

TL;DR

This paper introduces CLASS, a curriculum learning-based framework that improves cross-modal text-molecule retrieval by adaptively scheduling training samples and intensities, leading to better performance and efficiency.

Contribution

The paper proposes a novel curriculum learning approach for text-molecule retrieval that adaptively adjusts training difficulty and intensity, enhancing both accuracy and training efficiency.

Findings

Superior retrieval performance on ChEBI-20 dataset

Significant reduction in training time

Effective sample difficulty quantification

Abstract

Cross-modal text-molecule retrieval task bridges molecule structures and natural language descriptions. Existing methods predominantly focus on aligning text modality and molecule modality, yet they overlook adaptively adjusting the learning states at different training stages and enhancing training efficiency. To tackle these challenges, this paper proposes a Curriculum Learning-bAsed croSS-modal text-molecule training framework (CLASS), which can be integrated with any backbone to yield promising performance improvement. Specifically, we quantify the sample difficulty considering both text modality and molecule modality, and design a sample scheduler to introduce training samples via an easy-to-difficult paradigm as the training advances, remarkably reducing the scale of training samples at the early stage of training and improving training efficiency. Moreover, we introduce adaptive intensity learning to increase the training intensity as the training progresses, which adaptively controls the learning intensity across all curriculum stages. Experimental results on the ChEBI-20 dataset demonstrate that our proposed method gains superior performance, simultaneously achieving prominent time savings.