Metraipolis › archive › dc_445dc5c171b3

Causal graph fusion across incomplete cohorts and causal steering of tabular foundation models — arXiv:2611.09400

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.09400
License (as archived)
CC0-1.0
Archived
2026-11-09T22:41:35.355Z
SHA-256 of the archived text
fce30f4229d611ee8e98e71744f4e5fb1d5806c55cc3edb486ba85baf0d18b76
Stable URL of this page
https://metraipolis.com/documento/dc_445dc5c171b3

How to cite

Causal graph fusion across incomplete cohorts and causal steering of tabular foundation models — arXiv:2611.09400 — arXiv (en), https://arxiv.org/abs/2611.09400 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_445dc5c171b3 (Metraipolis archive dc_445dc5c171b3, sha256 fce30f4229d611ee8e98e71744f4e5fb1d5806c55cc3edb486ba85baf0d18b76)
BibTeX
@misc{dc445dc5c171b3,
  title = {Causal graph fusion across incomplete cohorts and causal steering of tabular foundation models — arXiv:2611.09400},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09400},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_445dc5c171b3; sha256 fce30f4229d611ee8e98e71744f4e5fb1d5806c55cc3edb486ba85baf0d18b76},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09400. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Clinical data are split across incomplete cohorts with partially overlapping variables. Causal discovery under missing data and multi-source integration have developed separately, and tabular foundation models cannot take a causal graph without retraining. We make two contributions. First, causal graph fusion learns a partial ancestral graph on the shared variables, fuses it into each cohort's graph under temporal background knowledge and lets Markov blankets guide re-imputation, so missing data are handled inside discovery. Second, causal attention steering compiles the learned graph into the attention of a frozen tabular foundation model at inference. Against known ground truth, fusion dominates pooled and per-cohort baselines in every missingness and heterogeneity condition tested (p<0.001), and steering improves discrimination under distribution shift (p<10^{-5}), a gain that a random graph does not produce. In two spinal cord injury cohorts, fusion orients age, albumin and hemoglobin as ancestors of length of stay, a set no single cohort orients in full, and yields compact, temporally ordered predictor sets that match or exceed automatic feature selection on four of five outcomes.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Applications (stat.AP).
Pagina del lavoro: https://arxiv.org/abs/2611.09400 — 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 2026-11-09T22:33:47.159Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).