Learning Non-Local Molecular Interactions via Equivariant Local Representations and Charge Equilibration
This addresses the challenge of efficiently capturing non-local interactions in molecular systems for computational chemistry, representing an incremental improvement by extending existing equivariant GNNs with a model-agnostic building block.
The paper tackled the problem of modeling long-range molecular interactions like charge transfer and electrostatic effects in Graph Neural Network potentials, which are limited by locality, by proposing the Charge Equilibration Layer for Long-range Interactions (CELLI), achieving state-of-the-art results for strictly local models on benchmark systems.
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.