Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

• URL: http://arxiv.org/abs/2603.11790v2
• Date: Wed, 18 Mar 2026 14:13:06 GMT
• Title: Disentangled Representation Learning through Unsupervised Symmetry Group Discovery
• Abstract summary: We show how an embodied subgroup autonomously discovers the group structure of its action space through unsupervised interaction with the environment.<n>We prove the identifiability of the true symmetry group decomposition under minimal assumptions.<n>Our method is validated on three environments exhibiting different group decompositions.
• Score: 2.3067587087700767
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Symmetry-based disentangled representation learning leverages the group structure of environment transformations to uncover the latent factors of variation. Prior approaches to symmetry-based disentanglement have required strong prior knowledge of the symmetry group's structure, or restrictive assumptions about the subgroup properties. In this work, we remove these constraints by proposing a method whereby an embodied agent autonomously discovers the group structure of its action space through unsupervised interaction with the environment. We prove the identifiability of the true symmetry group decomposition under minimal assumptions, and derive two algorithms: one for discovering the group decomposition from interaction data, and another for learning Linear Symmetry-Based Disentangled (LSBD) representations without assuming specific subgroup properties. Our method is validated on three environments exhibiting different group decompositions, where it outperforms existing LSBD approaches.

Related papers

• Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior [7.469447825853364]
  Group-Invariant Skill Discovery is a framework that embeds group structure into the skill discovery objective.<n>We show that GISD achieves broader state-space coverage and improved efficiency in downstream task learning compared to a strong baseline.
  arXiv  Detail & Related papers  (2026-01-20T14:21:18Z)
• Equivariance by Contrast: Identifiable Equivariant Embeddings from Unlabeled Finite Group Actions [18.11344454990819]
  We learn equivariant embeddings from observation pairs $(mathbfy, g cdot mathbfy)$, where $g$ is drawn from a finite group acting on the data.<n>Our method jointly learns a latent space and a group representation in which group actions correspond to invertible linear maps.
  arXiv  Detail & Related papers  (2025-10-24T17:59:46Z)
• Axis-level Symmetry Detection with Group-Equivariant Representation [48.813587457507786]
  Recent heatmap-based approaches can localize potential regions of symmetry axes but often lack precision in identifying individual axes.<n>We propose a novel framework for axis-level detection of the two most common symmetry types-reflection and rotation.<n>Our method achieves state-of-the-art performance, outperforming existing approaches.
  arXiv  Detail & Related papers  (2025-08-14T15:26:53Z)
• Relative Representations: Topological and Geometric Perspectives [50.85040046976025]
  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)
• Optimal Symmetries in Binary Classification [0.0]
  We show that selecting the appropriate group symmetries is crucial for optimising generalisation and sample efficiency. We develop a theoretical foundation for designing group equivariant neural networks that align the choice of symmetries with the underlying probability distributions of the data.
  arXiv  Detail & Related papers  (2024-08-16T16:15:18Z)
• Classifying symmetric and symmetry-broken spin chain phases with anomalous group actions [0.0]
  We consider the classification problem of quantum spin chains invariant under local decomposable group actions. We derive invariants for our classification that naturally cover one-dimensional symmetry protected topological phases.
  arXiv  Detail & Related papers  (2024-03-27T13:54:45Z)
• 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)
• Structure-preserving GANs [6.438897276587413]
  We introduce structure-preserving GANs as a data-efficient framework for learning distributions. We show that we can reduce the discriminator space to its projection on the invariant discriminator space. We contextualize our framework by building symmetry-preserving GANs for distributions with intrinsic group symmetry.
  arXiv  Detail & Related papers  (2022-02-02T16:40:04Z)
• GroupifyVAE: from Group-based Definition to VAE-based Unsupervised Representation Disentanglement [91.9003001845855]
  VAE-based unsupervised disentanglement can not be achieved without introducing other inductive bias. We address VAE-based unsupervised disentanglement by leveraging the constraints derived from the Group Theory based definition as the non-probabilistic inductive bias. We train 1800 models covering the most prominent VAE-based models on five datasets to verify the effectiveness of our method.
  arXiv  Detail & Related papers  (2021-02-20T09:49:51Z)
• LieTransformer: Equivariant self-attention for Lie Groups [49.9625160479096]
  Group equivariant neural networks are used as building blocks of group invariant neural networks. We extend the scope of the literature to self-attention, that is emerging as a prominent building block of deep learning models. We propose the LieTransformer, an architecture composed of LieSelfAttention layers that are equivariant to arbitrary Lie groups and their discrete subgroups.
  arXiv  Detail & Related papers  (2020-12-20T11:02:49Z)
• Constraints on Maximal Entanglement Under Groups of Permutations [73.21730086814223]
  Sets of entanglements are inherently equal, lying in the same orbit under the group action. We introduce new, generalized relationships for the maxima of those entanglement by exploiting the normalizer and normal subgroups of the physical symmetry group.
  arXiv  Detail & Related papers  (2020-11-30T02:21:22Z)

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.