---
res:
  bibo_abstract:
  - Research on recovering the latent factors of variation of high dimensional data
    has so far focused on simple synthetic settings. Mostly building on unsupervised
    and weakly-supervised objectives, prior work missed out on the positive implications
    for representation learning on real world data. In this work, we propose to leverage
    knowledge extracted from a diversified set of supervised tasks to learn a common
    disentangled representation. Assuming that each supervised task only depends on
    an unknown subset of the factors of variation, we disentangle the feature space
    of a supervised multi-task model, with features activating sparsely across different
    tasks and information being shared as appropriate. Importantly, we never directly
    observe the factors of variations, but establish that access to multiple tasks
    is sufficient for identifiability under sufficiency and minimality assumptions.
    We validate our approach on six real world distribution shift benchmarks, and
    different data modalities (images, text), demonstrating how disentangled representations
    can be transferred to real settings.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Marco
      foaf_name: Fumero, Marco
      foaf_surname: Fumero
  - foaf_Person:
      foaf_givenName: Florian
      foaf_name: Wenzel, Florian
      foaf_surname: Wenzel
  - foaf_Person:
      foaf_givenName: Luca
      foaf_name: Zancato, Luca
      foaf_surname: Zancato
  - foaf_Person:
      foaf_givenName: Alessandro
      foaf_name: Achille, Alessandro
      foaf_surname: Achille
  - foaf_Person:
      foaf_givenName: Emanuele
      foaf_name: Rodolà, Emanuele
      foaf_surname: Rodolà
  - foaf_Person:
      foaf_givenName: Stefano
      foaf_name: Soatto, Stefano
      foaf_surname: Soatto
  - foaf_Person:
      foaf_givenName: Bernhard
      foaf_name: Schölkopf, Bernhard
      foaf_surname: Schölkopf
  - foaf_Person:
      foaf_givenName: Francesco
      foaf_name: Locatello, Francesco
      foaf_surname: Locatello
      foaf_workInfoHomepage: http://www.librecat.org/personId=26cfd52f-2483-11ee-8040-88983bcc06d4
    orcid: 0000-0002-4850-0683
  bibo_volume: 36
  dct_date: 2023^xs_gYear
  dct_isPartOf:
  - http://id.crossref.org/issn/1049-5258
  dct_language: eng
  dct_publisher: Neural Information Processing Systems Foundation@
  dct_title: Leveraging sparse and shared feature activations for disentangled representation
    learning@
...