Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration

TL;DR

This paper introduces CELLI, a novel GNN layer that models long-range molecular interactions efficiently and accurately, extending local models to handle effects like charge transfer and electrostatics with high interpretability.

Contribution

The paper presents CELLI, a new layer that generalizes charge equilibration to improve GNNs' ability to model long-range interactions in molecular systems.

Findings

CELLI achieves state-of-the-art results on benchmark systems.

The method generalizes well to diverse datasets and large structures.

CELLI offers high computational efficiency and interpretability.

Abstract

Graph Neural Network (GNN) potentials relying on chemical locality offer near-quantum mechanical accuracy at significantly reduced computational costs. Message-passing GNNs model interactions beyond their immediate neighborhood by propagating local information between neighboring particles while remaining effectively local. However, locality precludes modeling long-range effects critical to many real-world systems, such as charge transfer, electrostatic interactions, and dispersion effects. In this work, we propose the Charge Equilibration Layer for Long-range Interactions (CELLI) to address the challenge of efficiently modeling non-local interactions. This novel architecture generalizes the classical charge equilibration (Qeq) method to a model-agnostic building block for modern equivariant GNN potentials. Therefore, CELLI extends the capability of GNNs to model long-range interactions while providing high interpretability through explicitly modeled charges. On benchmark systems, CELLI achieves state-of-the-art results for strictly local models. CELLI generalizes to diverse datasets and large structures while providing high computational efficiency and robust predictions.