A Commentary on the Unsupervised Learning of Disentangled Representations

  • Francesco Locatello ETH Zurich - Max Planck Institute for Intelligent Systems
  • Stefan Bauer Max Planck Institute for Intelligent Systems
  • Mario Lucic Google Research
  • Gunnar Rätsch ETH Zurich
  • Sylvain Gelly Google Research
  • Bernhard Schölkopf Max Planck Institute for Intelligent Systems
  • Olivier Bachem Google Research

Abstract

The goal of the unsupervised learning of disentangled representations is to separate the independent explanatory factors of variation in the data without access to supervision. In this paper, we summarize the results of (Locatello et al. 2019b) and focus on their implications for practitioners. We discuss the theoretical result showing that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases and the practical challenges it entails. Finally, we comment on our experimental findings, highlighting the limitations of state-of-the-art approaches and directions for future research.

Published
2020-04-03
Section
Sister Conference Track