Transferable FB-GNN-MBE Framework for Potential Energy Surfaces: Data-Adaptive Transfer Learning in Deep Learned Many-Body Expansion Theory

2026-04-10

AI Summary

Traditional first-principles methods struggle to efficiently and accurately predict potential energy surfaces for systems comprising hundreds of atoms or more. This work proposes a transferable fragment-based graph neural network many-body expansion framework (FB-GNN-MBE) that integrates quantum mechanical (QM) calculations with deep learning: single-fragment energies are obtained from QM computations, multi-fragment interactions are modeled using a fragment-based GNN (FB-GNN), and teacher–student transfer learning enables knowledge transfer across diverse systems. The approach achieves chemical accuracy in predicting two- and three-body interaction energies for water, phenol, and mixed systems, and generalizes successfully to water clusters of varying sizes without retraining. This significantly reduces both data requirements and computational cost, outperforming non-FB-GNN baseline models.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Mechanistic understanding and rational design of complex chemical systems depend on fast and accurate predictions of electronic structures beyond individual building blocks. However, if the system exceeds hundreds of atoms, first-principles quantum mechanical (QM) modeling becomes impractical. In this study, we developed FB-GNN-MBE by integrating a fragment-based graph neural network (FB-GNN) into the many-body expansion (MBE) theory and demonstrated its capacity to reproduce first-principles potential energy surfaces (PES) for hierarchically structured systems with manageable accuracy, complexity, and interpretability. Specifically, we divided the entire system into basic building blocks (fragments), evaluated their one-fragment energies using a QM model, and addressed many-fragment interactions using the structure-property relationships trained by FB-GNNs. Our investigation shows that FB-GNN-MBE achieves chemical accuracy in predicting two-body (2B) and three-body (3B) energies across water, phenol, and mixture benchmarks, as well as the one-dimensional dissociation curves of water and phenol dimers. To transfer the success of FB-GNN-MBE across various systems with minimal computational costs and data demands, we developed and validated a teacher-student learning protocol. A heavy-weight FB-GNN trained on a mixed-density water cluster ensemble (teacher) distills its learned knowledge and passes it to a light-weight GNN (student), which is later fine-tuned on a uniform-density (H2O)21 cluster ensemble. This transfer learning strategy resulted in efficient and accurate prediction of 2B and 3B energies for variously sized water clusters without retraining. Our transferable FB-GNN-MBE framework outperformed conventional non-FB-GNN-based models and showed high practicality for large-scale molecular simulations.

Problem

• potential energy surfaces
• many-body expansion
• transfer learning
• graph neural network
• quantum mechanical modeling

Innovation

• fragment-based graph neural network
• many-body expansion
• transfer learning
• potential energy surface
• teacher-student distillation