Abstract: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 will be made available upon publication.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2603.29475 [cs.LG] |
| (or arXiv:2603.29475v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.29475 arXiv-issued DOI via DataCite |
From: Dmitrii Seletkov [view email]
[v1]
Tue, 31 Mar 2026 09:22:52 UTC (7,986 KB)
[v2]
Wed, 13 May 2026 14:03:54 UTC (11,416 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。