Metraipolis › archive › dc_e50a83f03ffa
Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift — arXiv:2610.01143
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.01143
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T12:12:54.256Z
- SHA-256 of the archived text
4b6d8c828b8f0762145184b449ff5e458e92de2ff4b54b25985c67c64c9b54e2- Stable URL of this page
https://metraipolis.com/documento/dc_e50a83f03ffa
How to cite
Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift — arXiv:2610.01143 — arXiv (en), https://arxiv.org/abs/2610.01143 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e50a83f03ffa (Metraipolis archive dc_e50a83f03ffa, sha256 4b6d8c828b8f0762145184b449ff5e458e92de2ff4b54b25985c67c64c9b54e2)
BibTeX
@misc{dce50a83f03ffa,
title = {Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift — arXiv:2610.01143},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.01143},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e50a83f03ffa; sha256 4b6d8c828b8f0762145184b449ff5e458e92de2ff4b54b25985c67c64c9b54e2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.01143. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Despite strong mean accuracy, tabular foundation models (TFMs) can perform poorly on underrepresented groups under subpopulation shift, where group proportions change between training and deployment. We propose DR-TFM, a parameter-efficient distributionally robust adaptation framework that requires no true group annotations. DR-TFM adjusts attention to labeled context examples by fine-tuning an existing query scaling network or adding and training one, while keeping all other parameters fixed. We instantiate the framework with two robust objectives using estimated groups or source conditional distributions derived from training data. For TabPFN-3, adaptation updates only 0.016% of the pretrained model's parameters. Across five tabular benchmarks, DR-TFM achieves substantially higher average worst-group accuracy than pretrained TFMs and the compared robust baselines without true group annotations, while maintaining competitive mean group accuracy. DR-TFM also improves average worst-group accuracy on ACS Income and across four additional TFMs. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.01143 — 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 2026-10-06T10:21:28.157Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).