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. © 2020 Association for the Advancement of Artificial
Intelligence. Show more
Publication status
publishedExternal links
Journal / series
Proceedings of the AAAI Conference on Artificial IntelligenceVolume
Pages / Article No.
Publisher
AAAI PressEvent
Organisational unit
09568 - Rätsch, Gunnar / Rätsch, Gunnar
09664 - Schölkopf, Bernhard / Schölkopf, Bernhard
More
Show all metadata