arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.29475cs.LG
收藏

生存上下文:通过先验适应网络实现的 amortized 概率生存分析

Survival In-Context: Amortized Bayesian Survival Analysis via Prior-Fitted Networks

Institute of Diagnostic and Interventional Radiology, Technical University of Munich, Germany(慕尼黑技术大学诊断与介入放射学研究所,德国);Chair for AI in Healthcare and Medicine, Technical University of Munich, Germany(慕尼黑技术大学医疗人工智能与医学研究所,德国);Hasso Plattner Institute for Digital Engineering, University of Potsdam, Germany(波茨坦大学数字工程哈索普兰特纳研究所,德国);University Hospital Hamburg-Eppendorf, Germany(汉堡-埃彭多夫大学医院,德国);Department of Computing, Imperial College London, UK(伦敦帝国理工学院计算系,英国);Munich Center for Machine Learning (MCML), Germany(慕尼黑机器学习中心(MCML),德国)

Dmitrii Seletkov, Paul Hager, Georgios Kaissis, Rickmer Braren, Daniel Rueckert, Raphael Rehms

AI总结:

本文提出Survival In-Context模型,通过先验适应网络实现生存分析,无需任务特定训练即可进行个性化生存预测,实验证明其在小中等数据集上表现优异。

摘要:

生存分析在许多医疗应用中至关重要,但现代机器学习面临数据有限、删失和表格协变量异质性等挑战。虽然先验适应范式通过在大规模合成数据集上预训练模型促进了表格基础模型,但其在时间到事件建模中的适用性仍不明确。本文提出一个灵活的生存数据生成框架,定义了丰富的生存先验,可显式控制协变量和时间事件分布。基于此先验,我们引入Survival In-Context (SIC),一种通过合成数据预训练的上下文学习模型,用于生存分析。SIC被训练以近似在合成生存先验下的贝叶斯后验预测推断,能够在单次前向传递中实现个性化生存预测,无需任务特定训练或超参数调优。在广泛的现实生存数据集评估中,SIC在小中等数据集上表现优异,优于经典和深度生存模型,展示了先验适应范式在生存分析中的潜力。代码和预训练模型将在发表后提供。

英文摘要:

Survival analysis is crucial for many medical applications, but remains challenging for modern machine learning due to limited data, censoring, and the heterogeneity of tabular covariates. While the prior-fitted paradigm, which relies on pretraining models on large collections of synthetic datasets, has recently facilitated tabular foundation models for classification and regression, its suitability for time-to-event modeling remains unclear. We propose a flexible survival data generation framework that defines a rich survival prior with explicit control over covariates and time-event distributions. Building on this prior, we introduce Survival In-Context (SIC), a prior-fitted in-context learning model for survival analysis that is pretrained exclusively on synthetic data. SIC is trained to approximate Bayesian posterior predictive inference under the synthetic survival prior, enabling individualized survival prediction in a single forward pass, requiring no task-specific training or hyperparameter tuning. Across a broad evaluation on real-world survival datasets, SIC achieves competitive or superior performance compared to classical and deep survival models, particularly in small and medium-sized data regimes, highlighting the promise of a prior-fitted paradigm for survival analysis. The code and pretrained models are available at https://github.com/yayapa/sic

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。

↑