arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.04564cs.LG
收藏

SurvPFN:面向生存预测的基础模型

SurvPFN: Towards Foundation Models for Survival Predictions

University of Freiburg(弗赖堡大学)

Samuel Böhm, Lennart Purucker, Frank Hutter, Pascal Schlosser

AI总结:

提出SurvPFN,一种基于先验数据拟合网络(PFN)的生存预测模型,通过合成数据预训练和删失负对数似然损失,无需逐数据集拟合即可在真实任务中与经典和深度生存基线竞争。

摘要:

表格基础模型(TFM)在标准分类和回归任务中取得了快速进展,但时间至事件生存预测任务在很大程度上仍未涉及。与标准回归任务不同,生存预测模型必须处理删失数据。标准TFM无法原生处理删失数据,导致预测有偏且不准确,使其不适用于实际应用。为克服这一根本限制,我们提出了用于生存预测任务的先验数据拟合网络(PFN) exttt{SurvPFN}。我们在数百万个合成生存预测任务上预训练 exttt{SurvPFN},通过考虑删失数据的分布回归来学习生存。 exttt{SurvPFN}通过以下方式工作:(1)使用威布尔事件时间和非信息性删失机制生成数据;(2)整合删失事件指示符;(3)最小化删失负对数似然。在SurvSet(一个真实世界生存任务集合)上, exttt{SurvPFN}无需逐数据集拟合、生存特定架构或特征工程,即可与经典和深度生存基线高度竞争。我们表明,生存可以被视为具有删失损失的连续时间分布回归问题,从而释放PFN在时间至事件预测中的潜力。

英文摘要:

Tabular foundation models (TFMs) have made rapid progress in standard classification and regression, but time-to-event survival prediction tasks have remained largely untouched. Unlike in standard regression tasks, survival prediction models must account for censored data. Standard TFMs cannot handle natively censored data, leading to biased and inaccurate predictions, making them unsuitable for real-world applications. To overcome this fundamental limitation, we propose \texttt{SurvPFN}, a prior-data fitted network (PFN), for survival prediction tasks. We pretrain \texttt{SurvPFN} on millions of synthetic survival prediction tasks to learn survival via distributional regression that accounts for censored data. \texttt{SurvPFN} works by (1) generating data with Weibull event times and a non-informative censoring mechanism; (2) integrating a censored event indicator; and (3) minimizing a censored negative log-likelihood. On SurvSet, a collection of real-world survival tasks, \texttt{SurvPFN} is highly competitive with classical and deep survival baselines without per-dataset fitting, a survival-specific architecture, or feature engineering. We show that survival can be treated as a continuous-time distributional regression problem with censored loss, unlocking the power of PFNs for time-to-event predictions.

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。

↑