cs.LGJun 14, 2026

Scalar-pathway fidelity improves physical accuracy in short-range equivariant interatomic potentials

Authors: Jia Bi, Alin Marin Elena, Samuel Pinilla

Organizations: Science and Technology Facilities Council, Harwell Campus, Didcot, OX11 0QX, Oxfordshire, United Kingdom. · Science and Technology Facilities Council, Keckwick Lane, Daresbury, WA4 4AD, Cheshire, United Kingdom. · Diamond Light Source, Harwell Science and Innovation Campus,2026 Didcot, OX11 0QX, Oxfordshire, United Kingdom.

Abstract

Accurate interatomic potentials enable molecular dynamics of materials, molecules, and interfaces beyond density-functional-theory length and time scales. Equivariant neural network potentials have improved the representation of local geometry. However, their deployable energy surfaces ultimately manifest through invariant scalar channels, whose aggregation and spectral resolution remain comparatively underexamined. Here we use Physics-Aware Neighborhood (PAN) pooling and Physics-Guided Spectral (PGS) mixers as controlled scalar-pathway probes: lightweight, symmetry-preserving modifications that act only on ℓ=0\ell=0 channels while leaving the equivariant tensor backbone unchanged. Using MACE as a high-body-order mechanistic scaffold, PAN adds coordination-sensitive amplitude modulation, whereas PGS augments edge and readout scalar features with radial and tapered spectral bases. Across metallic Ag, covalent Si, a short-range ionic LiF/Li--F subset, and MD17/rMD17 molecules, this scalar-pathway correction reduces MACE force errors by 22--27% and energy errors by 19--22%; on systems with stress labels, stress errors decrease by 27--28%, at approximately 5% additional inference-FLOPs cost. Directionally consistent gains in Allegro and NequIP further indicate that the correction is portable across distinct short-range equivariant backbones, although effect sizes remain architecture-dependent. These results identify scalar-pathway fidelity as a practical design dimension for short-range equivariant interatomic potentials.

Explore similar work

CardsList
Jun 28, 2026physics.chem-ph

Geometric Algebra Meets Cartesian Tensors: Higher-Order Equivariance for Interatomic Potentials

Cl(3,0)\mathrm{Cl}(3,0) interatomic potentials, despite their algebraic elegance, predict force magnitudes accurately but force directions poorly. Across ten rMD17 molecules, every L≤1L \leq 1 baseline in our twelve-model study attains aggregate force-cosine similarity below 0.250.25. The cause is structural. The geometric product of two vectors in R3\mathbb{R}^3 realises only the L=0L=0 and L=1L=1 components of its irreducible representation content, leaving the symmetric-traceless rank-2 component absent from the per-edge bilinear that drives each message-passing layer. We address this with CliffordSTF, which couples the Clifford multivector to closed-form symmetric-traceless tensor tracks at ranks two and three through bilinear cross-track contractions, using a single learned bilinear and no Clebsch--Gordan tables, Wigner-DD matrices, or e3nn calls. On rMD17, CliffordSTF raises aggregate force-cosine similarity from 0.0550.055 (base Clifford) to 0.5510.551, an order-of-magnitude relative directional gain, alongside improved magnitude accuracy (force MAE 15.8%15.8\% lower; energy MAE 10.9%10.9\% lower). It outperforms all CG-free or body-ordered baselines in our study (all ≤0.17\leq 0.17). On catalysis benchmarks, CliffordSTF achieves the best out-of-distribution S2EF energy MAE on OC22 in our experiments, and the best in-distribution energy MAE among L≥2L \geq 2 methods on OC22 IS2RE. An eleven-variant ablation shows the two tracks are complementary: neither alone matches the combined model.
Can Polat, Erchin Serpedin, Mustafa Kurban +1
Interatomic PotentialsCosine SimilarityMolecular Structure ElucidationTensorHeterogeneous CatalysisExact Equivariance
AskPDF
Sep 28, 2025cs.LG

ADAPT: Lightweight, Long-Range Machine Learning Force Fields Without Graphs

Point defects play a central role in driving the properties of materials. First-principles methods are widely used to compute defect energetics and structures, including at scale for high-throughput defect databases. However, these methods are computationally expensive, making machine-learning force fields (MLFFs) an attractive alternative for accelerating structural relaxations. Most existing MLFFs are based on graph neural networks (GNNs), which can suffer from oversmoothing, oversquashing, and poor representation of long-range interactions. Both of these issues are especially of concern when modeling point defects. To address these challenges, we introduce the \textit{Accelerated Deep Atomic Potential Transformer} (ADAPT), an MLFF that replaces graph representations with a direct coordinates-in-space formulation and explicitly considers all pairwise atomic interactions. Atoms are treated as tokens, with a Transformer encoder modeling their interactions. Applied to a dataset of silicon point defects, ADAPT achieves a roughly 22% reduction in force and a roughly 40 percent reduction in energy prediction error relative to a state-of-the-art GNN-based model, while requiring only a fraction of the computational cost.
Evan Dramko, Yihuang Xiong, Yizhi Zhu +4
First-Principles CalculationMachine Learning
AskPDF
May 8, 2026cs.LG

Diagnosing Spectral Ceilings in Equivariant Neural Force Fields

We introduce a spectral-injection diagnostic for measuring which angular frequencies a trained equivariant force-field backbone preserves: inject a controlled angular-frequency perturbation into a molecular force field, attach a lightweight Spectral Prediction Network (SPN) to the frozen backbone, and read off which frequencies are recoverable. On aspirin, a quadratic SPN attached to an L = 2 NequIP backbone recovers the boundary signal at l = 4 but collapses at l = 5: a 11.7x cliff at the predicted drL boundary, with p dropping from 0.913 to 0.078. The same boundary-vs-above contrast persists across n = 4 independently trained backbones (raw-gain delta contrast, hierarchical cluster bootstrap) and is corroborated by a denominator-free injected-residual metric (R2_inj(4) = 0.374 versus R2_inj(5) = 0.006). A finite-degree span theorem calibrates the diagnostic: for a single marked direction, degree-d polynomials of degree-L spherical-harmonic features span exactly H less than or equal to dL with multiplicity-one saturation at the boundary (scoped to single-direction degree-bounded probes, not a function-class upper bound on multi-atom MPNNs). A synthetic C5 calibration plus capacity, activation, and cross-architecture controls rule out parameter count alone as the explanation.
Hyunmog Kim
SpectraFourierFrequency
AskPDF