SOURCE-LINKED INTELLIGENCE

Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Molecular property prediction requires representations that generalize from limited labeled data to structurally novel compounds. Existing molecular pretraining methods often rely on a single view: graph-based approaches model atom-bond topology but provide limited fragment-level supervision, whereas fingerprint descriptors encode chemical patterns but are typically used as fixed auxiliary features. We propose HiFi-Mol, a multi-view framework that separately pretrains a hierarchical graph encoder and a contextualized fingerprint encoder before downstream integration. The graph branch uses frag

Read original source ↗ Open in workspace

recordType

paper

region

Global