A Single Architecture for Representing Invariance Under Any Space Group

• URL: http://arxiv.org/abs/2512.13989v1
• Date: Tue, 16 Dec 2025 00:55:38 GMT
• Title: A Single Architecture for Representing Invariance Under Any Space Group
• Authors: Cindy Y. Zhang, Elif Ertekin, Peter Orbanz, Ryan P. Adams,
• Abstract summary: In materials science, symmetries are critical to modeling crystalline solids in materials science and condensed matter physics.<n>We present a new approach to such crystallographic symmetries by developing a single machine learning architecture that adapts its weights automatically to enforce invariance to any input space group.<n>We demonstrate the effectiveness of this approach in achieving competitive performance on material property prediction tasks and performing zero-shot learning to generalize to unseen groups.
• Score: 11.252916617394737
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Incorporating known symmetries in data into machine learning models has consistently improved predictive accuracy, robustness, and generalization. However, achieving exact invariance to specific symmetries typically requires designing bespoke architectures for each group of symmetries, limiting scalability and preventing knowledge transfer across related symmetries. In the case of the space groups, symmetries critical to modeling crystalline solids in materials science and condensed matter physics, this challenge is particularly salient as there are 230 such groups in three dimensions. In this work we present a new approach to such crystallographic symmetries by developing a single machine learning architecture that is capable of adapting its weights automatically to enforce invariance to any input space group. Our approach is based on constructing symmetry-adapted Fourier bases through an explicit characterization of constraints that group operations impose on Fourier coefficients. Encoding these constraints into a neural network layer enables weight sharing across different space groups, allowing the model to leverage structural similarities between groups and overcome data sparsity when limited measurements are available for specific groups. We demonstrate the effectiveness of this approach in achieving competitive performance on material property prediction tasks and performing zero-shot learning to generalize to unseen groups.

Related papers

• SEAL - A Symmetry EncourAging Loss for High Energy Physics [0.005211875900848231]
  Building machine learning models that explicitly respect symmetries can be difficult due to the dedicated components required.<n>We introduce soft constraints that allow the model to decide the importance of added symmetries during the learning process instead of enforcing exact symmetries.
  arXiv  Detail & Related papers  (2025-11-03T19:00:13Z)
• Generalized Linear Mode Connectivity for Transformers [87.32299363530996]
  A striking phenomenon is linear mode connectivity (LMC), where independently trained models can be connected by low- or zero-loss paths.<n>Prior work has predominantly focused on neuron re-ordering through permutations, but such approaches are limited in scope.<n>We introduce a unified framework that captures four symmetry classes: permutations, semi-permutations, transformations, and general invertible maps.<n>This generalization enables, for the first time, the discovery of low- and zero-barrier linear paths between independently trained Vision Transformers and GPT-2 models.
  arXiv  Detail & Related papers  (2025-06-28T01:46:36Z)
• Learning symmetries in datasets [0.0]
  We investigate how symmetries present in datasets affect the structure of the latent space learned by Variational Autoencoders (VAEs)<n>We show that when symmetries or approximate symmetries are present, the VAE self-organizes its latent space, effectively compressing the data along a reduced number of latent variables.<n>Our results highlight the potential of unsupervised generative models to expose underlying structures in data and offer a novel approach to symmetry discovery without explicit supervision.
  arXiv  Detail & Related papers  (2025-04-07T15:17:41Z)
• On the Ability of Deep Networks to Learn Symmetries from Data: A Neural Kernel Theory [0.0]
  In this work, we aim to understand when and how deep networks learn symmetries from data.<n>Inspired by real-world scenarios, we study a classification paradigm where data symmetries are only partially observed during training.<n>In the infinite-width limit, where kernel analogies apply, we derive a neural kernel theory of symmetry learning.
  arXiv  Detail & Related papers  (2024-12-16T07:56:54Z)
• Symmetry From Scratch: Group Equivariance as a Supervised Learning Task [1.8570740863168362]
  In machine learning datasets with symmetries, the paradigm for backward compatibility with symmetry-breaking has been to relax equivariant architectural constraints. We introduce symmetry-cloning, a method for inducing equivariance in machine learning models.
  arXiv  Detail & Related papers  (2024-10-05T00:44:09Z)
• Incorporating Arbitrary Matrix Group Equivariance into KANs [69.30866522377694]
  Kolmogorov-Arnold Networks (KANs) have seen great success in scientific domains.<n>We propose Equivariant Kolmogorov-Arnold Networks (EKAN) to broaden their applicability to more fields.
  arXiv  Detail & Related papers  (2024-10-01T06:34:58Z)
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks [79.16635054977068]
  We present a new class of equivariant neural networks, dubbed Lattice-Equivariant Neural Networks (LENNs) Our approach develops within a recently introduced framework aimed at learning neural network-based surrogate models Lattice Boltzmann collision operators. Our work opens towards practical utilization of machine learning-augmented Lattice Boltzmann CFD in real-world simulations.
  arXiv  Detail & Related papers  (2024-05-22T17:23:15Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles [55.41644538483948]
  We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the transformations symmetry and the corresponding generators. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.
  arXiv  Detail & Related papers  (2023-01-13T16:25:25Z)
• On the Symmetries of Deep Learning Models and their Internal Representations [1.418465438044804]
  We seek to connect the symmetries arising from the architecture of a family of models with the symmetries of that family's internal representation of data. Our work suggests that the symmetries of a network are propagated into the symmetries in that network's representation of data.
  arXiv  Detail & Related papers  (2022-05-27T22:29:08Z)
• Symmetry Group Equivariant Architectures for Physics [52.784926970374556]
  In the domain of machine learning, an awareness of symmetries has driven impressive performance breakthroughs. We argue that both the physics community and the broader machine learning community have much to understand.
  arXiv  Detail & Related papers  (2022-03-11T18:27:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.