# Graph Neural Network with Local Frame for Molecular Potential Energy Surface

Source: [Graph Neural Network with Local Frame for Molecular Potential Energy Surface](<https://www.sota2.com/research/paper/68fa44101e209131ce90e562>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T04:35:54.618Z

Authors: Xiyuan Wang, Muhan Zhang

Published: 2022-08-01T10:01:38.000Z

## Abstract

Modeling molecular potential energy surface is of pivotal importance in science. Graph Neural Networks have shown great success in this field. However, their message passing schemes need special designs to capture geometric information and fulfill symmetry requirement like rotation equivariance, leading to complicated architectures. To avoid these designs, we introduce a novel local frame method to molecule representation learning and analyze its expressivity. Projected onto a frame, equivariant features like 3D coordinates are converted to invariant features, so that we can capture geometric information with these projections and decouple the symmetry requirement from GNN design. Theoretically, we prove that given non-degenerate frames, even ordinary GNNs can encode molecules injectively and reach maximum expressivity with coordinate projection and frame-frame projection. In experiments, our model uses a simple ordinary GNN architecture yet achieves state-of-the-art accuracy. The simpler architecture also leads to higher scalability. Our model only takes about 30% inference time and 10% GPU memory compared to the most efficient baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Molecular Property Prediction on QM9 (test)](<https://www.sota2.com/research/sota/molecular-property-prediction-on-qm9-test.md>): Molecular property prediction; QM9 (test); mu: 0.013.

- [Energy and Force Prediction on MD17](<https://www.sota2.com/research/sota/energy-and-force-prediction-on-md17.md>): Energy and force prediction; MD17; Average Force Error (kcal/mol/Å): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2208.00716>)

[PDF](<https://arxiv.org/pdf/2208.00716.pdf>)