Can I read A Metric for Linear Symmetry-Based Disentanglement on EtoBox?

A Metric for Linear Symmetry-Based Disentanglement by Rey, Luis A. Pérez; Tonnaer, Loek; Menkovski, Vlado; Holenderski, Mike; Portegies, Jacobus W. is a scholarly article available to read on EtoBox.

What is A Metric for Linear Symmetry-Based Disentanglement about?

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.

Author

Rey, Luis A. Pérez; Tonnaer, Loek; Menkovski, Vlado; Holenderski, Mike; Portegies, Jacobus W.

Published

2020

Language

EN