GRAFT：分离排名与校准用于生存分析
GRAFT: Decoupling Ranking and Calibration for Survival Analysis
AI总结：
本文提出GRAFT模型，通过分离预测排名与生存校准，解决生存分析中排名与校准之间的权衡问题，该模型结合线性AFT模型与非线性残差神经网络，并利用随机门进行自动特征选择，从而在公开基准测试中实现了更好的判别能力和校准性能。
摘要：
生存分析受到删失数据、高维特征和非线性交互的挑战。经典模型提供可解释性和优越的校准能力，但局限于线性或预定义的功能形式，而深度学习模型具有灵活性并实现了强大的判别性能，但倾向于产生校准不佳的生存估计。为了解决这一权衡问题，我们提出GRAFT（Gated Residual Accelerated Failure Time），一种新的AFT模型，该模型将预测排名与生存校准分离。GRAFT的混合架构结合了线性AFT模型与非线性残差神经网络，并整合了随机门用于自动特征选择。该模型通过优化可微的、C-index对齐的排名损失进行训练，利用局部Kaplan-Meier估计器的随机条件插补，而校准的生存估计则通过简单的后训练校准获得。在公开基准测试中，GRAFT在判别能力和校准性能上优于基线模型，同时在高噪声设置中保持稳健和稀疏。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
