发表机构
University of Wisconsin–Madison; University of North Carolina at Chapel Hill（威斯康星大学麦迪逊分校; 北卡罗来纳大学教堂山分校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有分子-文本对齐方法忽略子结构与文本细粒度语义关系的问题，提出RISEN方法，通过检索构建孪生分子并结合相似度感知对比学习，在基准数据集上取得更优性能。
AI 中文摘要
本文研究分子-文本对齐问题，旨在将分子及其文本描述投影到联合潜在空间，以应用于分子搜索、分子属性预测等下游任务。现有方法通常将图结构挖掘与对比学习结合以增强联合表示学习，但往往忽略子结构与文本间的细粒度语义关系，导致下游任务性能欠佳。为此，我们提出一种名为RISEN（Retrieval-guided Twin Fusion with Similarity-aware Contrast）的新型分子-文本对齐方法。RISEN的核心思路是通过跨模态检索为每个子结构构建潜在孪生分子以实现语义增强：针对每个子结构查询，检索相关文本描述并采样多个具有相似子结构描述的分子，通过注意力池化聚合其表示得到孪生潜在表示，再将其与原始子结构融合以丰富表示；此外，我们测量子结构与文本间的相似度，通过软阈值化进一步指导跨模态对比学习。在基准数据集上的大量实验验证了所提RISEN相较于现有基线方法的优越性。
英文摘要
This paper studies the problem of molecule-text alignment, which aims to project molecules and their textual descriptions into a joint latent space for downstream tasks including molecule search and molecular property prediction. Previous approaches typically combine graph structure mining with contrastive learning to enhance joint representation learning. However, they typically neglect fine-grained semantic relationships between substructures and texts, leading to suboptimal performance on downstream tasks. Towards this end, we propose a novel approach named Retrieval-guided Twin Fusion with Similarity-aware Contrast (RISEN) for molecule-text alignment. The core idea of RISEN is to construct a latent twin molecule for each substructure with cross-modal retrieval for semantic enhancement. In particular, for each substructure query, we retrieve relevant textual descriptions and sample several molecules that share similar descriptions of substructures. Then, we aggregate their representations via attention pooling for a twin latent representation, which would be further fused with the original substructure for representation enrichment. In addition, we measure the similarity across substructures and texts, which would further guide cross-modal contrastive learning with soft thresholding. Extensive experiments on benchmark datasets validate the superiority of the proposed RISEN in comparison with existing baselines.
