Survival In-Context: Prior-fitted In-context Learning Tabular Foundation Model for Survival Analysis

2026-03-31

AI Summary

This work addresses the challenges of modeling in survival analysis posed by data scarcity, censoring, and covariate heterogeneity by proposing a synthetic-data-driven contextual learning framework. It introduces, for the first time, a prior-fitted contextual learning paradigm into survival analysis, leveraging a flexible survival data generator to pretrain deep neural networks. This approach enables zero-shot personalized survival prediction without requiring downstream fine-tuning or hyperparameter adjustment. Experimental results across multiple real-world datasets demonstrate that the proposed model matches or outperforms established classical and deep survival models, with particularly pronounced advantages in moderate-sized data regimes.

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 produces 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 medium-sized data regimes, highlighting the promise of prior-fitted foundation models for survival analysis. The code will be made available upon publication.

Problem

• survival analysis
• censoring
• tabular data
• time-to-event modeling
• data heterogeneity

Innovation

• survival analysis
• in-context learning
• tabular foundation model
• prior-fitted paradigm
• synthetic data generation