MCSA: Multi-Cutoff Spectral Aggregation in SO(3) Equivariant GNNs for Interatomic Potentials
Organizations: Kairos Materials · The University of Hong Kong · Tongji University · Westlake University ·
Abstract
Machine Learning Interatomic Potentials (MLIPs) based on Equivariant Graph Neural Networks (EGNNs) have achieved remarkable progress in atomistic modeling. However, accurately representing atomic interactions across different spatial scales remains challenging. In this work, we investigate the radial spectral properties of SO(3)-equivariant message passing and establish that the cutoff radius controls the characteristic spatial-frequency scale of radial interactions. Based on this analysis, we propose Multi-Cutoff Spectral Aggregation (MCSA), a plug-and-play module that aggregates radial kernels with different cutoff radii to enrich multi-scale geometric representations. To achieve efficient implementation, we exploit the compact support of radial kernels to fuse cutoff-dependent radial weights before angular tensor-product operations, avoiding redundant angular computations while preserving rotational equivariance. Extensive experiments across representative EGNN backbones demonstrate consistent improvements in energy, force, and stress prediction, as well as enhanced accuracy in higher-order properties, including phonon dispersion and lattice thermal conductivity. Further evaluations on layered materials with distinct interaction scales demonstrate the effectiveness of physically motivated cutoff selection. Code is available at: https://github.com/JF-Tan/MCSA.
Figures & tables
| Method | MPtrj (ID) | Alexandria (OOD) | ||||
|---|---|---|---|---|---|---|
| Energy | Force | Stress | Energy | Force | Stress | |
| Nequix | 14.2 | 40.4 | 0.273 | 41.8 | 75.5 | 0.366 |
| Nequix+MCSA | 13.4 | 38.7 | 0.267 | 39.9 | 74.3 | 0.354 |
| Eqnorm | 11.5 | 34.2 | 0.211 | 36.7 | 68.3 | 0.331 |
| Eqnorm+MCSA | 10.8 | 32.5 | 0.203 | 35.6 | 67.1 | 0.323 |
| EquiformerV3 | 6.3 | 18.1 | 0.151 | 22.1 | 43.5 | 0.217 |
| Model | Avg. Time (min/mat) | ( ) |
|---|---|---|
| Nequix | 1.107 | 0.487 |
| Nequix+MCSA | 1.136 | 0.420 |
| Variant | Cutoff Radii (Å) | RBF Size | Poly Degree | Inference Time | Params | MAE ( ) | |||
| Energy | Force | Stress | |||||||
| Baseline | 1 | 47 ms | 0.7M | 14.15 | 40.41 | 0.273 | |||
| Part I: Number and Placement of Cutoff Radii | |||||||||
| Two-scale | 2 | 50 ms | 0.9M | 13.70 | 39.25 | 0.268 | |||
| Three-scale (Ours) | 3 | 51 ms | 1.1M | 13.44 | 38.54 | 0.267 | |||
| Four-scale (A) | 4 | 54 ms | 1.3M | 13.57 | 38.87 | 0.269 | |||
Appendix figures & tables3 assets
Supplementary material from the paper’s appendix.
Appendix
| Hyper-parameters | Value |
|---|---|
| Optimizer | Muon |
| Learning rate scheduling | Cosine decay + linear warmup |
| Warmup epochs | |
| Maximum learning rate | |
| Batch size (per GPU) | |
| Weight decay |
| Hyper-parameters | Direct pre-training | Gradient fine-tuning |
| Optimizer | AdamW | AdamW |
| Learning rate scheduling | Cosine decay + linear warmup | Cosine decay + linear warmup |
| Warmup epochs | ||
| Maximum learning rate | ||
| Batch size (per GPU) | ||
| Number of epochs |
| Hyper-parameters | Value |
|---|---|
| Optimizer | Muon |
| Learning rate scheduling | Cosine decay + linear warmup |
| Warmup epochs | |
| Maximum learning rate | |
| Batch size (per GPU) | |
| Weight decay |
Machine Learning Interatomic Potentials
Machine learning interatomic potentials predict atomic energies and forces for fast simulations of molecules and materials.
See all 102 papers