Metraipolis › archive › dc_62b64dc06253

Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features — arXiv:2609.14902

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14902
License (as archived)
CC0-1.0
Archived
2026-10-16T00:15:39.636Z
SHA-256 of the archived text
e4d0876a870c353bb227f35fefeeb4279e0a0ca9fbb9c8045fa3270d03f9817d
Stable URL of this page
https://metraipolis.com/documento/dc_62b64dc06253

How to cite

Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features — arXiv:2609.14902 — arXiv (en), https://arxiv.org/abs/2609.14902 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62b64dc06253 (Metraipolis archive dc_62b64dc06253, sha256 e4d0876a870c353bb227f35fefeeb4279e0a0ca9fbb9c8045fa3270d03f9817d)
BibTeX
@misc{dc62b64dc06253,
  title = {Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features — arXiv:2609.14902},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14902},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62b64dc06253; sha256 e4d0876a870c353bb227f35fefeeb4279e0a0ca9fbb9c8045fa3270d03f9817d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14902. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Shapley value (SV)-based methods are the prevailing framework for feature attribution in machine learning, yet existing population-level Shapley estimators generally assume that observations used to evaluate the coalitional game are fully observed under a common feature space. This assumption is routinely violated in multi-site studies across biomedicine, social science, and environmental monitoring, where institutions record different features under different protocols, producing systematic blockwise missingness across sources. We first show that the standard remedy of imputing missing features before computing Shapley values introduces systematic, coalition-dependent bias into the resulting attributions. We then propose \textbf{FUSHAP} (\textbf{Fu}sion \textbf{Sh}apley \textbf{A}ttribution from \textbf{P}artially-observed data), a method that leverages partially-observed auxiliary sites to reduce the variance of a preliminary single-site Shapley estimate without imputation. A permutation-based screening step detects and excludes sites whose data distributions are incompatible with the target population. In synthetic experiments, FUSHAP achieves $3$--$8\times$ lower MSE than the single-site estimator and $2$--$3\times$ lower MSE than imputation baselines without incurring imputation-induced bias, and the screening procedure identifies misaligned sites with $82\%$ power at moderate misalignment and $100\%$ for strong misalignment. On multi-site air quality and multi-center clinical data, FUSHAP reduces MSE by approximately $3$--$7\times$ relative to the single-site estimator; in the clinical application, standard imputation can increase MSE above the single-site baseline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.14902 — 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 2026-10-15T23:54:14.930Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).