通过结构核心引导分子嵌入，可更有序地组织分子空间。
Structural Hierarchy and Geometry in Molecular Representation Learning
- 用分子骨架显式监督嵌入学习，引导模型理解结构关系。
- 骨架监督使分子按相似或相关骨架分组，提升属性预测性能。
- 洛伦兹几何下效果更强，但任务依赖性决定实际收益。
分子自监督学习利用化学结构来指导哪些分子嵌入应彼此相似。本文研究是否显式编码分子的Bemis-Murcko骨架，并用其监督分子嵌入，会如何影响模型所学内容。进一步通过对比欧氏与洛伦兹对比目标，检验嵌入几何对结果的影响。在两种增强强度下，骨架监督模型始终根据相同或结构相关的骨架组织分子。所得嵌入在多个分子属性预测任务中表现更好，具体提升程度取决于目标属性。骨架监督对分子组织的影响在洛伦兹目标下更强，但两种几何无一致整体优势。结果表明，显式教导分子与其结构核心的关系可可靠塑造分子嵌入空间的组织，但该组织的实用性仍取决于具体任务。
原文摘要 · Abstract (English)
Molecular self-supervised learning uses chemical structures to guide which molecular embeddings should be similar. We study whether explicitly encoding a molecule's Bemis-Murcko scaffold and using it to supervise the molecular embedding changes what the model learns. We further test whether this effect depends on the embedding geometry by comparing Euclidean and Lorentz contrastive objectives. Across two augmentation strengths, scaffold-supervised models consistently organize molecules according to both identical and structurally related scaffolds. The resulting embeddings also improve molecular property prediction on several tasks, while the exact gains depend on the predicted property. The effect of scaffold supervision on molecular organization is stronger under Lorentz objectives, but neither geometry provides a consistent overall advantage. These results show that explicitly teaching the relation between a molecule and its structural core can reliably shape the organization of molecular embedding space, while the extent of usefulness of this organization remains task dependent.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。