Metraipolis › archive › dc_89e0d5d87fcf

Why Tabular Foundation Models Excel on Relational Data They Have Never Seen — arXiv:2611.02936

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02936
License (as archived)
CC0-1.0
Archived
2026-11-03T10:54:20.779Z
SHA-256 of the archived text
9536bf9077cddd5bc5253c3b76595b45bf8771f5eb97ddcaa0dbea9766575a26
Stable URL of this page
https://metraipolis.com/documento/dc_89e0d5d87fcf

How to cite

Why Tabular Foundation Models Excel on Relational Data They Have Never Seen — arXiv:2611.02936 — arXiv (en), https://arxiv.org/abs/2611.02936 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89e0d5d87fcf (Metraipolis archive dc_89e0d5d87fcf, sha256 9536bf9077cddd5bc5253c3b76595b45bf8771f5eb97ddcaa0dbea9766575a26)
BibTeX
@misc{dc89e0d5d87fcf,
  title = {Why Tabular Foundation Models Excel on Relational Data They Have Never Seen — arXiv:2611.02936},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02936},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89e0d5d87fcf; sha256 9536bf9077cddd5bc5253c3b76595b45bf8771f5eb97ddcaa0dbea9766575a26},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02936. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Given a relational database (RDB) storing heterogeneous tabular information, how can we predict missing (or future) values in some target column of interest? As candidate targets are numerous in enterprise settings, it is preferable to avoid learning a new model from scratch each time there is a new prediction task. Frozen foundation models (FMs) based on in-context learning (ICL) and RDB-specific pre-training provide a viable solution, but the ideal design still remains largely unresolved. Perhaps unexpectedly, preliminary evidence has recently shown that existing single-table FMs (aka TFMs), when combined with suitable parameter-free relational encoders, can be quite competitive in practice despite zero exposure to RDB pre-training or relational data of any kind. In this work we first empirically confirm this phenomenon with a more diverse array of experiments. We then turn to our main contribution, namely, surfacing multiple complementary explanations for why TFMs behave so effectively. These explanations ultimately hinge on innate synergies whereby parameter-free encoders map relational effects to fixed-length embeddings that loosely mimic distributions for which TFMs were originally designed; in so doing, desirable single-table properties transfer to relational settings (e.g., convergent posterior predictive distributions). Collectively, our analysis forges new pathways for improving RDB FMs, particularly when we prioritize interpretability and inevitable integration within agentic systems.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Databases (cs.DB); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.02936 — 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 2026-11-03T10:49:38.401Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).