English

Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs

Machine Learning 2024-09-27 v1 Artificial Intelligence

Abstract

Geometric graph neural networks (GNNs) have emerged as powerful tools for modeling molecular geometry. However, they encounter limitations in effectively capturing long-range interactions in large molecular systems. To address this challenge, we introduce Neural P3^3M, a versatile enhancer of geometric GNNs to expand the scope of their capabilities by incorporating mesh points alongside atoms and reimaging traditional mathematical operations in a trainable manner. Neural P3^3M exhibits flexibility across a wide range of molecular systems and demonstrates remarkable accuracy in predicting energies and forces, outperforming on benchmarks such as the MD22 dataset. It also achieves an average improvement of 22% on the OE62 dataset while integrating with various architectures.

Keywords

Cite

@article{arxiv.2409.17622,
  title  = {Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs},
  author = {Yusong Wang and Chaoran Cheng and Shaoning Li and Yuxuan Ren and Bin Shao and Ge Liu and Pheng-Ann Heng and Nanning Zheng},
  journal= {arXiv preprint arXiv:2409.17622},
  year   = {2024}
}

Comments

Published as a conference paper at NeurIPS 2024

R2 v1 2026-06-28T18:57:48.218Z