Heterogeneous relational message passing networks for molecular dynamics simulations

TL;DR

HermNet is a novel heterogeneous graph neural network designed for molecular dynamics simulations, effectively modeling diverse interactions with ab initio accuracy and outperforming many existing models on multiple datasets.

Contribution

This work introduces HermNet, a universal heterogeneous relational message passing network that captures multiple interactions in molecular systems more effectively than homogeneous models.

Findings

HermNet outperforms other models on MD17, QM9, and extended systems datasets.

HermNet achieves near state-of-the-art accuracy with ab initio quality.

The design aligns with quantum mechanics principles from density functional theory.

Abstract

With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties, machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics, material science, chemistry, and biology. While existing machine learning models have yielded superior performances in many occasions, most of them model and process molecular systems in terms of homogeneous graph, which severely limits the expressive power for representing diverse interactions. In practice, graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems. Thus, we propose the heterogeneous relational message passing network (HermNet), an end-to-end heterogeneous graph neural networks, to efficiently express multiple interactions in a single model with {\it ab initio} accuracy. HermNet performs impressively against many top-performing models on both molecular and extended systems. Specifically, HermNet outperforms other tested models in nearly 75\%, 83\% and 94\% of tasks on MD17, QM9 and extended systems datasets, respectively. Finally, we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory. Besides, HermNet is a universal framework, whose sub-networks could be replaced by other advanced models.