5 Downloads (Pure)

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 $SO(2)$ symmetries.
Original languageEnglish
Publication statusPublished - 26 Nov 2020
EventNeurIPS 2020 workshop on Differential Geometry meets Deep Learning - Online
Duration: 11 Dec 202011 Dec 2020
https://sites.google.com/view/diffgeo4dl/call-for-papers?authuser=0

Workshop

WorkshopNeurIPS 2020 workshop on Differential Geometry meets Deep Learning
Abbreviated titleDiffGeo4DL
Period11/12/2011/12/20
Internet address

Keywords

  • cs.LG

Cite this