Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks

• URL: http://arxiv.org/abs/2509.24886v1
• Date: Mon, 29 Sep 2025 14:59:46 GMT
• Title: Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
• Authors: Ya-Wei Eileen Lin, Ron Levie,
• Abstract summary: We introduce emphadaptive canonicalization, a general framework for enforcing symmetry in neural networks.<n>We prove that this construction yields continuous and symmetry-respecting models that admit universal approximation properties.<n>We propose two applications of our setting: (i) resolving eigenbasis in spectral graph neural networks, and (ii) handling rotational symmetries in point clouds.
• Score: 22.039672459015453
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Canonicalization is a widely used strategy in equivariant machine learning, enforcing symmetry in neural networks by mapping each input to a standard form. Yet, it often introduces discontinuities that can affect stability during training, limit generalization, and complicate universal approximation theorems. In this paper, we address this by introducing \emph{adaptive canonicalization}, a general framework in which the canonicalization depends both on the input and the network. Specifically, we present the adaptive canonicalization based on prior maximization, where the standard form of the input is chosen to maximize the predictive confidence of the network. We prove that this construction yields continuous and symmetry-respecting models that admit universal approximation properties. We propose two applications of our setting: (i) resolving eigenbasis ambiguities in spectral graph neural networks, and (ii) handling rotational symmetries in point clouds. We empirically validate our methods on molecular and protein classification, as well as point cloud classification tasks. Our adaptive canonicalization outperforms the three other common solutions to equivariant machine learning: data augmentation, standard canonicalization, and equivariant architectures.

Related papers

• Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation [56.361076943802594]
  CanonFlow achieves state-of-the-art performance on the challenging GEOM-DRUG dataset, and the advantage remains large in few-step generation.
  arXiv  Detail & Related papers  (2026-02-16T18:58:55Z)
• Towards A Unified PAC-Bayesian Framework for Norm-based Generalization Bounds [63.47271262149291]
  We propose a unified framework for PAC-Bayesian norm-based generalization.<n>The key to our approach is a sensitivity matrix that quantifies the network outputs with respect to structured weight perturbations.<n>We derive a family of generalization bounds that recover several existing PAC-Bayesian results as special cases.
  arXiv  Detail & Related papers  (2026-01-13T00:42:22Z)
• Preconditioned Norms: A Unified Framework for Steepest Descent, Quasi-Newton and Adaptive Methods [50.070182958880146]
  We propose a unified framework generalizing descent, quasi-Newton methods, and adaptive methods through the novel notion of preconditioned matrix norms.<n>Within this framework, we provide the first systematic treatment of affine and scale invariance in the matrix- parameterized setting.<n>We introduce two new methods, $ttMuAdam$ and $texttMuAdam-SANIA$, which combine the spectral geometry of Muon with Adam-style preconditioning.
  arXiv  Detail & Related papers  (2025-10-12T19:39:41Z)
• Equivariance by Local Canonicalization: A Matter of Representation [11.697651699958755]
  We present a framework to transfers existing tensor field networks into the more efficient local canonicalization paradigm.<n>Within this framework, we systematically compare different equivariant representations in terms of theoretical complexity, empirical runtime, and predictive accuracy.
  arXiv  Detail & Related papers  (2025-09-30T16:41:18Z)
• Improving Equivariant Networks with Probabilistic Symmetry Breaking [9.164167226137664]
  Equivariant networks encode known symmetries into neural networks, often enhancing generalizations.<n>This poses an important problem, both (1) for prediction tasks on domains where self-symmetries are common, and (2) for generative models, which must break symmetries in order to reconstruct from highly symmetric latent spaces.<n>We present novel theoretical results that establish sufficient conditions for representing such distributions.
  arXiv  Detail & Related papers  (2025-03-27T21:04:49Z)
• Relative Representations: Topological and Geometric Perspectives [53.88896255693922]
  Relative representations are an established approach to zero-shot model stitching.<n>We introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations.<n>Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes.
  arXiv  Detail & Related papers  (2024-09-17T08:09:22Z)
• Metric Convolutions: A Unifying Theory to Adaptive Image Convolutions [3.481985817302898]
  Metric convolutions are a novel approach that samples unit balls from explicit signal-dependent metrics.<n>This framework can directly replace existing convolutions applied to either input images or deep features of neural networks.<n>Our approach shows competitive performance in standard denoising and classification tasks.
  arXiv  Detail & Related papers  (2024-06-08T08:41:12Z)
• A Canonicalization Perspective on Invariant and Equivariant Learning [54.44572887716977]
  We introduce a canonicalization perspective that provides an essential and complete view of the design of frames. We show that there exists an inherent connection between frames and canonical forms. We design novel frames for eigenvectors that are strictly superior to existing methods.
  arXiv  Detail & Related papers  (2024-05-28T17:22:15Z)
• Orthogonal Transforms in Neural Networks Amount to Effective Regularization [0.0]
  We consider applications of neural networks in nonlinear system identification. We show that such a structure is a universal approximator. We empirically show in particular, that such a structure, using the Fourier transform, outperforms equivalent models without orthogonality support.
  arXiv  Detail & Related papers  (2023-05-10T17:52:33Z)
• Equivariance with Learned Canonicalization Functions [77.32483958400282]
  We show that learning a small neural network to perform canonicalization is better than using predefineds. Our experiments show that learning the canonicalization function is competitive with existing techniques for learning equivariant functions across many tasks.
  arXiv  Detail & Related papers  (2022-11-11T21:58:15Z)
• Generalization capabilities of neural networks in lattice applications [0.0]
  We investigate the advantages of adopting translationally equivariant neural networks in favor of non-equivariant ones. We show that our best equivariant architectures can perform and generalize significantly better than their non-equivariant counterparts.
  arXiv  Detail & Related papers  (2021-12-23T11:48:06Z)
• Stochastic batch size for adaptive regularization in deep network optimization [63.68104397173262]
  We propose a first-order optimization algorithm incorporating adaptive regularization applicable to machine learning problems in deep learning framework. We empirically demonstrate the effectiveness of our algorithm using an image classification task based on conventional network models applied to commonly used benchmark datasets.
  arXiv  Detail & Related papers  (2020-04-14T07:54:53Z)

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.