Timezone: »

Weakly-Supervised Disentanglement Without Compromises
Francesco Locatello · Ben Poole · Gunnar Ratsch · Bernhard Schölkopf · Olivier Bachem · Michael Tschannen

Tue Jul 14 12:00 PM -- 12:45 PM & Wed Jul 15 01:00 AM -- 01:45 AM (PDT) @ None #None

Intelligent agents should be able to learn useful representations by observing changes in their environment. We model such observations as pairs of non-i.i.d. images sharing at least one of the underlying factors of variation. First, we theoretically show that only knowing how many factors have changed, but not which ones, is sufficient to learn disentangled representations. Second, we provide practical algorithms that learn disentangled representations from pairs of images without requiring annotation of groups, individual factors, or the number of factors that have changed. Third, we perform a large-scale empirical study and show that such pairs of observations are sufficient to reliably learn disentangled representations on several benchmark data sets. Finally, we evaluate our learned representations and find that they are simultaneously useful on a diverse suite of tasks, including generalization under covariate shifts, fairness, and abstract reasoning. Overall, our results demonstrate that weak supervision enables learning of useful disentangled representations in realistic scenarios.

Author Information

Francesco Locatello (ETH Zurich - Max Planck Institute)
Ben Poole (Google Brain)
Gunnar Ratsch (ETH Zurich)
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)
Michael Tschannen (Google Brain)

More from the Same Authors