Metraipolis › archive › dc_04db7cc23c45
Training Fair Tabular Foundation Models — arXiv:2608.14211
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.14211
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T02:21:26.710Z
- SHA-256 of the archived text
a220d06b86c1e13434ceb70fa26a256aef977b37cecfaec6b0ca6bdf48c954ee- Stable URL of this page
https://metraipolis.com/documento/dc_04db7cc23c45
How to cite
Training Fair Tabular Foundation Models — arXiv:2608.14211 — arXiv (en), https://arxiv.org/abs/2608.14211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_04db7cc23c45 (Metraipolis archive dc_04db7cc23c45, sha256 a220d06b86c1e13434ceb70fa26a256aef977b37cecfaec6b0ca6bdf48c954ee)
BibTeX
@misc{dc04db7cc23c45,
title = {Training Fair Tabular Foundation Models — arXiv:2608.14211},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.14211},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_04db7cc23c45; sha256 a220d06b86c1e13434ceb70fa26a256aef977b37cecfaec6b0ca6bdf48c954ee},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.14211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, leveraging in-context learning to predict on new data without task-specific training. Despite the increased use of TFMs in high-stakes decision-making, their fairness properties remain largely unexplored. In this work, we incorporate fairness constraints directly into TFM training, enabling fair predictions in a single forward pass. Our approach addresses two key challenges: limited access to sensitive attributes in training data, and the incompatibility of existing fairness techniques with the in-context learning paradigm. We propose FairTFM, a scalable training strategy based on synthetic fairness tasks and a fairness-aware architecture using a gradient reversal layer, which encourages the model to learn representations invariant to sensitive attributes. Experiments on 132 fairness tasks show consistent improvements in fairness while maintaining competitive accuracy. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-17 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.14211 — 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 2026-10-19T02:02:02.925Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).