Graph Fourier Neural ODEs: Bridging Spatial and Temporal Multiscales in Molecular Dynamics

Molecular dynamics simulations are crucial for understanding complex physical, chemical, and biological processes at the atomic level. However, accurately capturing interactions across multiple spatial and temporal scales remains a significant challenge. We present a novel framework that jointly models spatial and temporal multiscale interactions in molecular dynamics. Our approach leverages Graph Fourier Transforms to decompose molecular structures into different spatial scales and employs Neural Ordinary Differential Equations to model the temporal dynamics in a curated manner influenced by the spatial modes. This unified framework links spatial structures with temporal evolution in a flexible manner, enabling more accurate and comprehensive simulations of molecular systems. We evaluate our model on the MD17 dataset, demonstrating consistent performance improvements over state-of-the-art baselines across multiple molecules, particularly under challenging conditions such as irregular timestep sampling and long-term prediction horizons. Ablation studies confirm the significant contributions of both spatial and temporal multiscale modeling components. Our method advances the simulation of complex molecular systems, potentially accelerating research in computational chemistry, drug discovery, and materials science.

@article{sun2025_2411.01600,
  title={ Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamics },
  author={ Fang Sun and Zijie Huang and Haixin Wang and Huacong Tang and Xiao Luo and Wei Wang and Yizhou Sun },
  journal={arXiv preprint arXiv:2411.01600},
  year={ 2025 }
}