Timezone: »

 
Desiderata for Representation Learning from Identifiability, Disentanglement, and Group-Structuredness
Hamza Keurti · Patrik Reizinger · Bernhard Schölkopf · Wieland Brendel

Fri Jul 28 02:10 PM -- 03:00 PM (PDT) @
in 2nd Annual Workshop on Topology, Algebra, and Geometry in Machine Learning (TAG-ML) »
Event URL: https://openreview.net/forum?id=r6C86JjuiW »

Machine learning subfields define useful representations differently: disentanglement strives for semantic meaning and symmetries, identifiability for recovering the ground-truth factors of the (unobservable) data generating process, group-structured representations for equivariance. We demonstrate that despite their merits, each approach has shortcomings. Surprisingly, joining forces helps overcome the limitations: we use insights from latent space statistics, geometry, and topology in our examples to elucidate how combining the desiderata of identifiability, disentanglement, and group structure yields more useful representations.

Author Information

Hamza Keurti (MPI-IS)
Patrik Reizinger (Eberhard-Karls-Universität Tübingen)
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.

Wieland Brendel (University of Tübingen)

More from the Same Authors