Rotation-Invariant Machine Learning for Highly Symmetric Molecular Configurations
Atomistic machine learning can approximate expensive quantum mechanical calculations at a fraction of their computational cost, but accuracy depends strongly on how the three-dimensional atomic environments are represented. Invariant representations enable fast computation but can fail to distinguish geometrically distinct configurations, especially in highly symmetric environments. We introduce a lightweight benchmark to evaluate expressivity on $n$-fold symmetric configurations, and use it to expose degeneracies in both invariant and equivariant architectures. Guided by these results, we construct a new invariant basis for HIP-HOP which resolves most of the identified failures. On a methane simulation dataset, the extended basis achieves the lowest error among the HIP-HOP variants and has similar accuracy to EquiformerV3 while running $3.2\times$ faster at inference. These results show that carefully constructed invariant representations can mitigate key expressivity limitations while balancing accuracy and computational efficiency.
Authors
- Nicholas Lubbers (ORCID: https://orcid.org/0000-0002-9001-9973)
- Alice E. A. Allen (ORCID: https://orcid.org/0000-0002-8727-8333)
- Roxana Bujack (ORCID: https://orcid.org/0000-0002-5479-3726)
- Tomáš Karella (ORCID: https://orcid.org/0000-0002-4090-8422)
- Pieter J. Swart
- Emily Shinkle (ORCID: https://orcid.org/0000-0003-2255-0540)
- Logan Bolton
- Nathaniel Philip Gorski
Publication Details
- Journal
- arXiv (Cornell University)
- Published
- 2026-11-16
- DOI
- https://doi.org/10.48550/arxiv.2611.21308
- Primary Topic
- Machine Learning in Materials Science
- Type
- preprint