@article{Locatello_Bauer_Lucic_Rätsch_Gelly_Schölkopf_Bachem_2020, title={A Commentary on the Unsupervised Learning of Disentangled Representations}, volume={34}, url={https://ojs.aaai.org/index.php/AAAI/article/view/7120}, DOI={10.1609/aaai.v34i09.7120}, abstractNote={<p>The goal of the <em>unsupervised</em> learning of <em>disentangled</em> 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.</p>}, number={09}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Locatello, Francesco and Bauer, Stefan and Lucic, Mario and Rätsch, Gunnar and Gelly, Sylvain and Schölkopf, Bernhard and Bachem, Olivier}, year={2020}, month={Apr.}, pages={13681-13684} }