Multi-Level Fusion Graph Neural Network for Molecule Property Prediction
By: XiaYu Liu , Chao Fan , Yang Liu and more
Potential Business Impact:
Finds new medicines faster by understanding molecules.
Accurate prediction of molecular properties is essential in drug discovery and related fields. However, existing graph neural networks (GNNs) often struggle to simultaneously capture both local and global molecular structures. In this work, we propose a Multi-Level Fusion Graph Neural Network (MLFGNN) that integrates Graph Attention Networks and a novel Graph Transformer to jointly model local and global dependencies. In addition, we incorporate molecular fingerprints as a complementary modality and introduce a mechanism of interaction between attention to adaptively fuse information across representations. Extensive experiments on multiple benchmark datasets demonstrate that MLFGNN consistently outperforms state-of-the-art methods in both classification and regression tasks. Interpretability analysis further reveals that the model effectively captures task-relevant chemical patterns, supporting the usefulness of multi-level and multi-modal fusion in molecular representation learning.
Similar Papers
Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding
Machine Learning (CS)
Helps computers understand chemicals better using words and shapes.
Improving Predictions of Molecular Properties with Graph Featurisation and Heterogeneous Ensemble Models
Machine Learning (CS)
Predicts how molecules will act better.
Combining Graph Neural Networks and Mixed Integer Linear Programming for Molecular Inference under the Two-Layered Model
Machine Learning (CS)
Designs new molecules with useful properties.