paper-with-me

Papers

Learning Group Structure and Disentangled Representations of Dynamical Environments

2020-02-17 · Robin Quessard, Thomas D. Barrett, William R. Clements

Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe in terms of symmetry preserving transformations. Inspired by this formalism, we propose a framework, built upon the theory of group representation, for learning representations of a dynamical environment structured around the transformations that generate its evolution. Experimentally, we learn the structure of explicitly symmetric environments without supervision from observational data generated by sequential interactions. We further introduce an intuitive disentanglement regularisation to ensure the interpretability of the learnt representations. We show that our method enables accurate long-horizon predictions, and demonstrate a correlation between the quality of predictions and disentanglement in the latent space.

📄 PDF Abstract BibTeX arXiv:2002.06991

Code (1)

IndustAI/learning-group-structure 공식 구현 pytorch

Tasks

Disentanglement

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Learning Disentangled Representations and Group Structure of Dynamical Environments

2020-12-01 · NeurIPS 2020 12 · Robin Quessard, Thomas Barrett, William Clements

Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the unive…

Disentanglement

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 require…

Representation Learning

Learning Group Actions In Disentangled Latent Image Representations

2025-12-03 · Farhana Hossain Swarnali, Miaomiao Zhang, Tonmoy Hossain arxiv

Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transformations typically operate in the high-…

Learning Abstract World Models with a Group-Structured Latent Space

2025-06-02 · Thomas Delliaux, Nguyen-Khanh Vu, Vincent François-Lavet, Elise van der Pol 외

Learning meaningful abstract models of Markov Decision Processes (MDPs) is crucial for improving generalization from limited data. In this work, we show how geometric priors can be imposed on the low-dimensional represen…

Group-disentangled Representation Learning with Weakly-Supervised Regularization

2021-10-23 · Linh Tran, Amir Hosein Khasahmadi, Aditya Sanghi, Saeid Asgari

Learning interpretable and human-controllable representations that uncover factors of variation in data remains an ongoing key challenge in representation learning. We investigate learning group-disentangled representati…

DisentanglementRepresentation LearningTransfer Learning