Saved in:
Bibliographic Details
Main Authors: Liu, Xiayu, Lu, Zhengyi, Liao, Yunhong, Fan, Chan, Li, Hou-biao
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.22610
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-global multimodal contrastive learning framework that jointly models molecular graphs and textual representations derived from SMILES and chemistry-aware augmented texts. Local functional group information and global molecular topology are captured using AttentiveFP and Graph Transformer encoders, respectively, and aligned through self-supervised contrastive learning. In addition, chemically enriched textual descriptions are contrasted with original SMILES to incorporate physicochemical semantics in a task-agnostic manner. During fine-tuning, molecular fingerprints are further integrated via Dual Cross-attention multimodal fusion. Extensive experiments on MoleculeNet benchmarks demonstrate that LGM-CL achieves consistent and competitive performance across both classification and regression tasks, validating the effectiveness of unified local-global and multimodal representation learning.