GRAFT: Decoupling Ranking and Calibration for Survival Analysis

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ashhad, Mohammad, Hoehndorf, Robert, Henao, Ricardo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917504236912640
author Ashhad, Mohammad
Hoehndorf, Robert
Henao, Ricardo
author_facet Ashhad, Mohammad
Hoehndorf, Robert
Henao, Ricardo
contents Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretability and superior calibration but are restricted to linear or predefined functional forms, while deep learning models are flexible and achieve strong discriminative performance, but tend to produce poorly calibrated survival estimates. To address this trade-off, we propose GRAFT (Gated Residual Accelerated Failure Time), a novel AFT model that decouples prognostic ranking from survival calibration. GRAFT's hybrid architecture combines a linear AFT model with a non-linear residual neural network, and it also integrates stochastic gates for automatic feature selection. The model is trained by optimizing a differentiable, C-index-aligned ranking loss using stochastic conditional imputation from local Kaplan-Meier estimators, while calibrated survival estimates are obtained through simple post-training calibration. In public benchmarks, GRAFT outperforms baselines in discrimination and calibration, while remaining robust and sparse in high-noise settings.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07884
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle GRAFT: Decoupling Ranking and Calibration for Survival Analysis
Ashhad, Mohammad
Hoehndorf, Robert
Henao, Ricardo
Machine Learning
Artificial Intelligence
Survival analysis is complicated by censored data, high-dimensional features, and non-linear interactions. Classical models offer interpretability and superior calibration but are restricted to linear or predefined functional forms, while deep learning models are flexible and achieve strong discriminative performance, but tend to produce poorly calibrated survival estimates. To address this trade-off, we propose GRAFT (Gated Residual Accelerated Failure Time), a novel AFT model that decouples prognostic ranking from survival calibration. GRAFT's hybrid architecture combines a linear AFT model with a non-linear residual neural network, and it also integrates stochastic gates for automatic feature selection. The model is trained by optimizing a differentiable, C-index-aligned ranking loss using stochastic conditional imputation from local Kaplan-Meier estimators, while calibrated survival estimates are obtained through simple post-training calibration. In public benchmarks, GRAFT outperforms baselines in discrimination and calibration, while remaining robust and sparse in high-noise settings.
title GRAFT: Decoupling Ranking and Calibration for Survival Analysis
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2602.07884