A Metric for Linear Symmetry-Based Disentanglement
Machine Learning
2020-11-30 v1
Abstract
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 symmetries.
Cite
@article{arxiv.2011.13306,
title = {A Metric for Linear Symmetry-Based Disentanglement},
author = {Luis A. Pérez Rey and Loek Tonnaer and Vlado Menkovski and Mike Holenderski and Jacobus W. Portegies},
journal= {arXiv preprint arXiv:2011.13306},
year = {2020}
}