mlsanityData to 7 Oct 2026

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

arXiv 1904.00243 ↗First posted 30 Mar 2019cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

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. Higgins et al. recently proposed Symmetry-Based Disentangled Representation Learning, a definition based on a characterization of symmetries in the environment using group theory. We build on their work and make observations, theoretical and empirical, that lead us to argue that Symmetry-Based Disentangled Representation Learning cannot only be based on static observations: agents should interact with the environment to discover its symmetries. Our experiments can be reproduced in Colab and the code is available on GitHub.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 12; 2023: 7; 2024: 2; 2025: 2; 2026: 5.

35 papers.

Sort:

By area:

  1. 2022Disentangled Representation Learningcited by 111
  2. 2021Learning Disentangled Representations in the Imaging Domaincited by 46
  3. 2023Latent Space Symmetry Discoverycited by 29
  4. 2021Commutative Lie Group VAE for Disentanglement Learningcited by 27
  5. 2021Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamicscited by 27
  6. 2022Symmetry-Based Representations for Artificial and Biological General Intelligencecited by 26
  7. 2022Continuous MDP Homomorphisms and Homomorphic Policy Gradientcited by 24
  8. 2021Towards Building A Group-based Unsupervised Representation Disentanglement Frameworkcited by 22
  9. 2022Toward Compositional Generalization in Object-Oriented World Modelingcited by 22
  10. 2022Homomorphism Autoencoder -- Learning Group Structured Representations from Observed Transitionscited by 18
  11. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  12. 2021Addressing the Topological Defects of Disentanglement via Distributed Operatorscited by 14
23 more
  1. 2023Policy Gradient Methods in the Presence of Symmetries and State Abstractionscited by 8
  2. 2021Hamiltonian latent operators for content and motion disentanglement in image sequencescited by 5
  3. 2023Topological Obstructions and How to Avoid Themcited by 4
  4. 2024SiT: Symmetry-Invariant Transformers for Generalisation in Reinforcement Learningcited by 3
  5. 2025What Drives Compositional Generalization in Visual Generative Models? The Importance of Continuous Training Objectivescited by 3
  6. 2023Enriching Disentanglement: From Logical Definitions to Quantitative Metricscited by 2
  7. 2023Algebras of actions in an agent's representations of the worldcited by 2
  8. 2021VECA : A Toolkit for Building Virtual Environments to Train and Test Human-like Agentscited by 1
  9. 2022Equivariant Disentangled Transformation for Domain Generalization under Combination Shiftcited by 1
  10. 2024Measuring Orthogonality in Representations of Generative Modelscited by 1
  11. 2026Groupoid-Based Internal State Representations for Reinforcement Learning with Local Symmetriescited by 1
  12. 2022Transformation Coding: Simple Objectives for Equivariant Representationscited by 0
  13. 2022On a Built-in Conflict between Deep Learning and Systematic Generalizationcited by 0
  14. 2022Learning Parsimonious Dynamics for Generalization in Reinforcement Learningcited by 0
  15. 2022A Short Survey of Systematic Generalizationcited by 0
  16. 2022Symmetry Detection in Trajectory Data for More Meaningful Reinforcement Learning Representationscited by 0
  17. 2023Switchable Lightweight Anti-symmetric Processing (SLAP) with CNN Outspeeds Data Augmentation by Smaller Sample -- Application in Gomoku Reinforcement Learningcited by 0
  18. 2023Equivariant Representation Learning in the Presence of Stabilizerscited by 0
  19. 2025Developmental Symmetry-Loss: A Free-Energy Perspective on Brain-Inspired Invariance Learningcited by 0
  20. 2026Disentangled Representation Learning through Unsupervised Symmetry Group Discoverycited by 0
  21. 2026Investigating Permutation-Invariant Discrete Representation Learning for Spatially Aligned Imagescited by 0
  22. 2026Disentanglement Beyond Generative Models with Riemannian ICAcited by 0
  23. 2026Categorical Internalisation of Environmental Groupoids for Generalisable POMDP Solvingcited by 0