Poster
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
Francesco Locatello · Stefan Bauer · Mario Lucic · Gunnar Raetsch · Sylvain Gelly · Bernhard Schölkopf · Olivier Bachem

Tue Jun 11th 06:30 -- 09:00 PM @ Pacific Ballroom #271
The key idea behind the unsupervised learning of disentangled representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this paper, we provide a sober look at recent progress in the field and challenge some common assumptions. We first theoretically show that the unsupervised learning of disentangled representations is fundamentally impossible without inductive biases on both the models and the data. Then, we train more than $12000$ models covering most prominent methods and evaluation metrics in a reproducible large-scale experimental study on seven different data sets. We observe that while the different methods successfully enforce properties ``encouraged'' by the corresponding losses, well-disentangled models seemingly cannot be identified without supervision. Furthermore, increased disentanglement does not seem to lead to a decreased sample complexity of learning for downstream tasks. Our results suggest that future work on disentanglement learning should be explicit about the role of inductive biases and (implicit) supervision, investigate concrete benefits of enforcing disentanglement of the learned representations, and consider a reproducible experimental setup covering several data sets.

Author Information

Francesco Locatello (ETH Zurich - Max Planck Institute)
Stefan Bauer (MPI for Intelligent Systems)
Mario Lucic (Google Brain)
Gunnar Raetsch (ETH Zurich)
Sylvain Gelly (Google Brain)
Bernhard Schölkopf (MPI for Intelligent Systems Tübingen, Germany)

Bernhard Scholkopf received degrees in mathematics (London) and physics (Tubingen), and a doctorate in computer science from the Technical University Berlin. He has researched at AT&T Bell Labs, at GMD FIRST, Berlin, at the Australian National University, Canberra, and at Microsoft Research Cambridge (UK). In 2001, he was appointed scientific member of the Max Planck Society and director at the MPI for Biological Cybernetics; in 2010 he founded the Max Planck Institute for Intelligent Systems. For further information, see www.kyb.tuebingen.mpg.de/~bs.

Olivier Bachem (Google Brain)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors