Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Disentangled Representation Learning through Unsupervised Symmetry Group Discovery

About

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.

Barth\'el\'emy Dang-Nhu, Louis Annabi, Sylvain Argentieri• 2026

Related benchmarks

TaskDatasetResultRank
Disentanglement3DShapes
DCI Score1
22
DisentanglementCOIL3
Beta-VAE1
15
Disentangled Representation LearningFlatLand rotation colors
Beta-VAE Score1
15
DisentanglementCOIL 2
Beta-VAE100
15
DisentanglementFlatLand permutation colors
Beta-VAE1
15
DisentanglementMPI3D
Modularity Score49
14
Prediction ErrorCOIL2 iid restricted (test)
Seen Prediction Error6.10e-5
6
Prediction ErrorCOIL2 ood restricted (right-most rotation) (test)
Seen Prediction Error6.20e-5
6
DisentanglementCOIL3 (iid)
Beta-VAE100
5
DisentanglementCOIL3 (ood)
Beta-VAE100
5
Showing 10 of 14 rows

Other info

Follow for update