Metraipolis › archive › dc_944e7486afe2

KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure — arXiv:2611.00264

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00264
License (as archived)
CC0-1.0
Archived
2026-11-03T18:35:06.905Z
SHA-256 of the archived text
ba1983e2fa354bdeefc4dafe2434a6d0192ff612863b1f8f8830b820ffe4a4b7
Stable URL of this page
https://metraipolis.com/documento/dc_944e7486afe2

How to cite

KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure — arXiv:2611.00264 — arXiv (en), https://arxiv.org/abs/2611.00264 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_944e7486afe2 (Metraipolis archive dc_944e7486afe2, sha256 ba1983e2fa354bdeefc4dafe2434a6d0192ff612863b1f8f8830b820ffe4a4b7)
BibTeX
@misc{dc944e7486afe2,
  title = {KINDER: Kernel-based Independence for Fair Representation Learning via Prototype-space Erasure — arXiv:2611.00264},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00264},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_944e7486afe2; sha256 ba1983e2fa354bdeefc4dafe2434a6d0192ff612863b1f8f8830b820ffe4a4b7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00264. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Concept erasure is a prominent approach to achieving fairness in machine learning through the removal of sensitive attributes from learned representations. Prior concept erasure methods typically define debiasing indirectly through the failure of a chosen adversary, probe, or fairness penalty, which makes the target of erasure dependent on a particular decoder family or optimization setup. We introduce KINDER, which directly removes sensitive-attribute information from intermediate representations with respect to a chosen family of prototype functionals, and is compatible with any deep model containing an intermediate feature space, independent of the architecture, task type, or training paradigm. KINDER operates in a random Fourier feature space, where it estimates a sensitive subspace from protected group prototypes and projects representations onto its orthogonal complement. Thus, it forms an explicit representation cleaning mechanism distinct from prior fairness control studies. We conduct extensive experiments across diverse settings and show the effectiveness of KINDER on (i) supervised and self-supervised settings, (ii) classification, regression, and image segmentation tasks, and (iii) diverse data modalities, including visual, textual, and tabular data. Code and trained models are available at: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Machine Learning (stat.ML).
Pagina del lavoro: https://arxiv.org/abs/2611.00264 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T18:12:54.407Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).