Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jiele, Ma, Haozhe, Guo, Zhihan, Vo, Thanh Vinh, Leong, Tze Yun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908849700601856
author Wu, Jiele
Ma, Haozhe
Guo, Zhihan
Vo, Thanh Vinh
Leong, Tze Yun
author_facet Wu, Jiele
Ma, Haozhe
Guo, Zhihan
Vo, Thanh Vinh
Leong, Tze Yun
contents Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus on node- or edge-level information, often ignoring chemically relevant substructures which strongly influence molecular properties. In this work, we propose Graph Semantic Predictive Network (GraSPNet), a hierarchical self-supervised framework that explicitly models both atomic-level and fragment-level semantics. GraSPNet decomposes molecular graphs into chemically meaningful fragments without predefined vocabularies and learns node- and fragment-level representations through multi-level message passing with masked semantic prediction at both levels. This hierarchical semantic supervision enables GraSPNet to learn multi-resolution structural information that is both expressive and transferable. Extensive experiments on multiple molecular property prediction benchmarks demonstrate that GraSPNet learns chemically meaningful representations and consistently outperforms state-of-the-art GSSL methods in transfer learning settings.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20344
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction
Wu, Jiele
Ma, Haozhe
Guo, Zhihan
Vo, Thanh Vinh
Leong, Tze Yun
Machine Learning
Artificial Intelligence
Quantitative Methods
Graph self-supervised learning (GSSL) has demonstrated strong potential for generating expressive graph embeddings without the need for human annotations, making it particularly valuable in domains with high labeling costs such as molecular graph analysis. However, existing GSSL methods mostly focus on node- or edge-level information, often ignoring chemically relevant substructures which strongly influence molecular properties. In this work, we propose Graph Semantic Predictive Network (GraSPNet), a hierarchical self-supervised framework that explicitly models both atomic-level and fragment-level semantics. GraSPNet decomposes molecular graphs into chemically meaningful fragments without predefined vocabularies and learns node- and fragment-level representations through multi-level message passing with masked semantic prediction at both levels. This hierarchical semantic supervision enables GraSPNet to learn multi-resolution structural information that is both expressive and transferable. Extensive experiments on multiple molecular property prediction benchmarks demonstrate that GraSPNet learns chemically meaningful representations and consistently outperforms state-of-the-art GSSL methods in transfer learning settings.
title Hierarchical Molecular Representation Learning via Fragment-Based Self-Supervised Embedding Prediction
topic Machine Learning
Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2602.20344