A Metric for Linear Symmetry-Based Disentanglement

The definition of Linear Symmetry-Based Disentanglement (LSBD) proposed by (Higgins et al., 2018) outlines the properties that should characterize a disentangled representation that captures the symmetries of data. However, it is not clear how to measure the degree to which a data representation ful...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Pérez Rey, Luis A, Tonnaer, Loek, Menkovski, Vlado, Holenderski, Mike, Portegies, Jacobus W
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.11.2020
Subjects
Evaluation
Representations
Symmetry
Online AccessGet full text

Cover

More Information
Summary:The definition of Linear Symmetry-Based Disentanglement (LSBD) proposed by (Higgins et al., 2018) outlines the properties that should characterize a disentangled representation that captures the symmetries of data. However, it is not clear how to measure the degree to which a data representation fulfills these properties. We propose a metric for the evaluation of the level of LSBD that a data representation achieves. We provide a practical method to evaluate this metric and use it to evaluate the disentanglement of the data representations obtained for three datasets with underlying \(SO(2)\) symmetries.
ISSN:2331-8422