Integrating equivariant architectures and charge supervision for data-efficient molecular property prediction
Molecular equivariant transformer (MET) learns symmetry-aware, charge-guided representations that capture geometric and electronic structure, enabling data-efficient and interpretable molecular property prediction across diverse tasks.
Authors
- Zixiao Yang
Institutions
- Hong Kong University of Science and Technology (HK)
- South China University of Technology (CN)
Publication Details
- Journal
- Molecular Systems Design & Engineering
- Published
- 2025-12-24
- DOI
- https://doi.org/10.1039/d5me00173k
- Primary Topic
- Machine Learning in Materials Science
- Type
- article
- Field-Weighted Citation Impact
- 0.00