Abstract
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.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Kim, S., Jo, S., & Chae, M. (2026). Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift. https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift
MLA 9
Kim, Seonghwi, et al. "Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift." https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift.
Chicago (author–date)
Kim, Seonghwi, Sungho Jo, and Minwoo Chae. 2026. "Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift." https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift.
Harvard
Kim, S., Jo, S. and Chae, M. (2026) 'Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift', Available at: https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift.
Vancouver
Kim S, Jo S, Chae M. Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift. https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift
IEEE
S. Kim, S. Jo, and M. Chae, "Parameter-Efficient Distributionally Robust Adaptation of Tabular Foundation Models under Subpopulation Shift," https://omanscience.com/en/articles/parameter-efficient-distributionally-robust-adaptation-of-tabular-foundation-models-under-subpopulation-shift.