Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights

• URL: http://arxiv.org/abs/2607.03108v1
• Date: Fri, 03 Jul 2026 08:43:47 GMT
• Title: Observable- and Positional-Encoding-Dependent Symmetry Readout from Neural Network Weights
• Abstract summary: Post-hoc analysis of trained neural network weights often seeks to recover geometric structure directly from the parameters.<n>We show that, for positional-encoding-separated neural fields, the symmetry visible from weights is not the true symmetry group itself, but an observable symmetry set determined by the trained parameters.
• Score: 2.595513192756607
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Post-hoc analysis of trained neural network weights often seeks to recover geometric structure directly from the parameters. We show that, for positional-encoding-equipped neural fields, the symmetry visible from weights is not the true symmetry group itself, but an observable symmetry set determined by the trained parameters, the positional encoding (PE), and readout observable. We formulate this dependence through an exact observability hierarchy, $G_{\mathrm{obs}}^{\mathrm{exact}} \subseteq G_{\mathrm{lift}}^{\mathrm{exact}}(φ) \cap G_{\mathrm{true}}$, where $G_{\mathrm{lift}}^{\mathrm{exact}}(φ)$ is the set of input transformations that the PE can exactly lift to the feature space. The hierarchy implies that even when a target function has a geometric symmetry, that symmetry may be structurally invisible to weight-level observables if the PE does not represent the corresponding transformation. We test this prediction using MLPs trained on two-dimensional signed distance functions with multiple shape symmetry groups, positional encodings, and Gram-based observables. The results show a consistent PE-dependent pattern: DyadicAxisPE supports $D_4$-sensitive readout but structurally suppresses $D_3$ rotations, TriAxisPE yields lower $D_3$ / $D_6$ readout scores under the tested Gram observables by replacing coordinate axes with three 120-degree-separated axes, and random Fourier features mainly exhibit a $π$-rotation response under these readouts. These findings show that PE design affects not only approximation behavior but also which structures are accessible to post-hoc weight-level readouts. This provides a basis for a principled observable-dependent symmetry readout.

Related papers

• $\ ext{GSF-}χ$: Global Stereochemical Fields for Chiral Graph Transformers [49.85093436361195]
  We introduce GSF-$$, a graph transformer in which stereogenic units modulate all pairwise interactions.<n>A $C$ projection separates mirror-even ECD peak counts and positions from mirror-odd peak signs.<n>GSF-$$ leads every central-ECD output and improves axial Rotation and Symbol by $12.6%$ and $7.9%$ over the strongest baseline.
  arXiv  Detail & Related papers  (2026-09-11T07:41:20Z)
• Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability [51.56484100374058]
  We prove the first identifiability theorem for a mechanistic-interpretability primitive.<n>The spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.
  arXiv  Detail & Related papers  (2026-08-10T19:42:01Z)
• Spin-Weighted Spherical Harmonics Enable Complete and Scalable $\mathrm{E}(3)$-Equivariant Networks [46.25293959572394]
  We present SpinGTP, an approach to overcome the GTP incompleteness.<n>We evaluate SpinGTP across diverse benchmarks, including Tetris, 3BPA, SPICE-MACE-OFF, and OC20.<n>This work provides a complete, scalable, and mathematically rigorous path toward high-order equivariant in large-scale 3D atomistic system simulations.
  arXiv  Detail & Related papers  (2026-07-01T19:13:44Z)
• An Information-Geometric Justification for Composite Coherence in Event-Based Narrative Extraction [0.27074235008521247]
  We study the composite metric $C=sqrtAcdot T$, where $A$ is the angular similarity of document embeddings and $T=1-d_mathrmJS$.<n>Experiments on four corpora, three embedding families, and three topic models are consistent with the framework.
  arXiv  Detail & Related papers  (2026-06-28T00:05:15Z)
• Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery [17.340037184664208]
  We introduce the $star_G$ tensor algebra, in which any finite group $G$ defines the algebraic multiplication rule.<n>The framework provides capabilities that redesign neural networks (ENNs) structurally cannot: a closed-form per-irreducible equi- decomposition of every prediction, and data-driven discovery of the symmetry group that best fits a dataset.
  arXiv  Detail & Related papers  (2026-05-19T19:47:40Z)
• Interpretable Machine Learning for Spatial Science: A Lie-Algebraic Kernel for Rotationally Anisotropic Gaussian Processes [0.0]
  Three-dimensional spatial fields are anisotropic, with directions of rapid and slow variation that need not align with coordinate axes.<n>Standard Gaussian process kernels with Automatic Relevance Determination (ARD) capture only axis-aligned anisotropy.<n>We introduce an interpretable rotationally anisotropic GP kernel that parameterises a three-dimensional SPD covariance metric.
  arXiv  Detail & Related papers  (2026-05-11T19:42:47Z)
• Robust inverse material design with physical guarantees using the Voigt-Reuss Net [0.0]
  We propose a spectrally normalized surrogate for forward and inverse mechanical homogenization with hard physical guarantees.<n>In 3D linear elasticity on an open dataset of biphasic microstructures, a fully connected Voigt-Reuss net trained on $>!7.5times 105$ FFT-based labels with 236 isotropy-in descriptors.<n>Overall, the Voigt-Reuss net unifies accurate, physically admissible forward prediction with large-batch, constraint-consistent inverse design.
  arXiv  Detail & Related papers  (2025-11-14T15:17:37Z)
• Mesoscopic Fluctuations and Multifractality at and across Measurement-Induced Phase Transition [46.176861415532095]
  We explore statistical fluctuations over the ensemble of quantum trajectories in a model of two-dimensional free fermions.<n>Our results exhibit a remarkable analogy to Anderson localization, with $G_AB$ corresponding to two-terminal conductance.<n>Our findings lay the groundwork for mesoscopic theory of monitored systems, paving the way for various extensions.
  arXiv  Detail & Related papers  (2025-07-15T13:44:14Z)
• Symmetry-Breaking Descent for Invariant Cost Functionals [0.0]
  We study the problem of reducing a task cost functional $W : Hs(M) to mathbbR$, not assumed continuous or differentiable.<n>We show that symmetry-breaking deformations of the signal can reduce the cost.
  arXiv  Detail & Related papers  (2025-05-19T15:06:31Z)
• Scale Equivariant Graph Metanetworks [20.445135424921908]
  This paper pertains to an emerging machine learning paradigm: learning functions whose inputs are functions themselves. We propose $textitScale Equivariant Graph MetaNetworks - ScaleGMNs$, a framework that adapts the Graph Metanetwork (message-passing) paradigm by incorporating scaling symmetries.
  arXiv  Detail & Related papers  (2024-06-15T16:41:04Z)
• A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features [26.619014249559942]
  We present a mathematical formulation for machine learning of functions on symmetric matrices and point clouds.<n>We provide a general construction of generically separating invariant features using ideas inspired by Galois theory.<n>We prove that the number of invariant features can be reduced, generically without losing expressivity, to $O(n)$, where $n$ is the number of points.
  arXiv  Detail & Related papers  (2024-05-13T18:24:03Z)
• 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)
• Towards Antisymmetric Neural Ansatz Separation [48.80300074254758]
  We study separations between two fundamental models of antisymmetric functions, that is, functions $f$ of the form $f(x_sigma(1), ldots, x_sigma(N)) These arise in the context of quantum chemistry, and are the basic modeling tool for wavefunctions of Fermionic systems.
  arXiv  Detail & Related papers  (2022-08-05T16:35:24Z)

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.