Metraipolis › archive › dc_0dbf210cce9c

Source projection for calibrated transfer learning in survival prediction — arXiv:2610.41230

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.41230
License (as archived)
CC0-1.0
Archived
2026-11-02T04:55:27.114Z
SHA-256 of the archived text
656e280128c5fc5e49759e63cecd139538a55d01b65896a274b87d233c1e5654
Stable URL of this page
https://metraipolis.com/documento/dc_0dbf210cce9c

How to cite

Source projection for calibrated transfer learning in survival prediction — arXiv:2610.41230 — arXiv (en), https://arxiv.org/abs/2610.41230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0dbf210cce9c (Metraipolis archive dc_0dbf210cce9c, sha256 656e280128c5fc5e49759e63cecd139538a55d01b65896a274b87d233c1e5654)
BibTeX
@misc{dc0dbf210cce9c,
  title = {Source projection for calibrated transfer learning in survival prediction — arXiv:2610.41230},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41230},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0dbf210cce9c; sha256 656e280128c5fc5e49759e63cecd139538a55d01b65896a274b87d233c1e5654},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Transfer learning can improve survival prediction in cohorts with few events. An external model may capture useful covariate associations yet systematically overestimate or underestimate risk in the target population, creating a need for selective borrowing. We propose Source Projection Transfer (SPT) for fixed-horizon prediction with a target generalized additive model. SPT requires only source predictions at target covariates, supporting generalized additive, Cox and neural-network source models without individual-level source data. It projects source log-odds scores onto the target basis and borrows through two separately adapted channels: a projection-centered penalty transfers effect shapes, while intercept-recalibrated soft labels inform probabilities at the target risk level. Under local asymptotics, projection avoids the strictly positive risk cost of estimating an uninformative additional source direction. Each channel asymptotically switches off under its corresponding persistent-mismatch condition. In log-logistic and Weibull simulations with covariate shift, SPT improves mean Brier score and discrimination over target-only modeling in all 24 setting-distribution-horizon combinations. Matched comparisons show improvements over borrowing through source probabilities alone across settings, and over borrowing the complete source score under structural mismatch. In UK Biobank-to-SPRINT mortality prediction among standard-treatment participants with reduced kidney function, SPT improves mean discrimination at 24, 30 and 36 months, with Brier improvements at 24 and 36 months. SPT enables flexible source learners to inform a parsimonious target model while adapting to differences between populations.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv stat.ME, nuovi lavori del giorno).
Categorie arXiv: Methodology (stat.ME).
Pagina del lavoro: https://arxiv.org/abs/2610.41230 — 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 2026-11-02T04:46:12.632Z dalla pagina https://arxiv.org/list/stat.ME/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).