Equivariant Graph Network Approximations of High-Degree Polynomials for Force Field Prediction
This work addresses the need for accurate and generalizable force field predictions in molecular dynamics, which is crucial for computational chemistry and materials science, representing an incremental improvement over existing equivariant models.
The authors tackled the problem of predicting atomic potentials and force fields in molecular dynamics simulations by introducing PACE, an equivariant network that approximates high-degree equivariant polynomial functions, achieving state-of-the-art performance in benchmarks with robust generalization across temperature conditions.
Recent advancements in equivariant deep models have shown promise in accurately predicting atomic potentials and force fields in molecular dynamics simulations. Using spherical harmonics (SH) and tensor products (TP), these equivariant networks gain enhanced physical understanding, like symmetries and many-body interactions. Beyond encoding physical insights, SH and TP are also crucial to represent equivariant polynomial functions. In this work, we analyze the equivariant polynomial functions for the equivariant architecture, and introduce a novel equivariant network, named PACE. The proposed PACE utilizes edge booster and the Atomic Cluster Expansion (ACE) technique to approximate a greater number of $SE(3) \times S_n$ equivariant polynomial functions with enhanced degrees. As experimented in commonly used benchmarks, PACE demonstrates state-of-the-art performance in predicting atomic energy and force fields, with robust generalization capability across various geometric distributions under molecular dynamics (MD) across different temperature conditions. Our code is publicly available as part of the AIRS library https://github.com/divelab/AIRS/.