paper-with-me

Papers

Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

2026-03-12 · Barthélémy Dang-Nhu, Louis Annabi, Sylvain Argentieri arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.11790

Code (0)

등록된 구현이 없습니다.

Tasks

Representation Learning

Similar Papers 제목 키워드 기반

Linear Disentangled Representations and Unsupervised Action Estimation

2020-08-18 · NeurIPS 2020 12 · Matthew Painter, Jonathon Hare, Adam Prugel-Bennett

Disentangled representation learning has seen a surge in interest over recent times, generally focusing on new models which optimise one of many disparate disentanglement metrics. Symmetry Based Disentangled Representati…

DisentanglementRepresentation Learning

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

2019-03-30 · NeurIPS 2019 12 · Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat

Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents…

Representation Learning

Algebras of actions in an agent's representations of the world

2023-10-02 · Alexander Dean, Eduardo Alonso, Esther Mondragon

In this paper, we propose a framework to extract the algebra of the transformations of worlds from the perspective of an agent. As a starting point, we use our framework to reproduce the symmetry-based representations fr…

Representation Learning

Equivariant Representation Learning via Class-Pose Decomposition

2022-07-07 · Giovanni Luca Marchetti, Gustaf Tegnér, Anastasiia Varava, Danica Kragic

We introduce a general method for learning representations that are equivariant to symmetries of data. Our central idea is to decompose the latent space into an invariant factor and the symmetry group itself. The compone…

Representation Learning

SymmetryLens: A new candidate paradigm for unsupervised symmetry learning via locality and equivariance

2024-10-07 · Onur Efe, Arkadas Ozakin

We develop a new, unsupervised symmetry learning method that starts with raw data, and gives the minimal (discrete) generator of an underlying Lie group of symmetries, together with a symmetry equivariant representation …

Translation