用上下文学习实现无需调参的生存分析，一次前向传播搞定预测。
SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference
- 基于合成数据预训练，通过上下文学习实现贝叶斯推断
- 在61个数据集上超越21种方法，性能强且分布校准好
- 适合医疗、金融等需处理删失数据的领域快速应用
生存分析为存在删失的数据提供了强大的统计框架。然而，从众多专用方法中选择合适的估计器通常需要大量的方法论和领域知识。我们提出SurvivalPFN，一种通过上下文学习对删失观测进行贝叶斯推断的先验-数据拟合网络。该模型在多样化的合成、可识别及右删失数据生成过程中预训练，能够在推理时仅通过一次前向传播完成生存分析。因此，模型能自适应每个数据集的有效复杂度，无需任务特定训练或超参数调优，避免了严格的参数假设，并生成校准良好的生存分布。在涵盖61个数据集、21种方法和5项评估指标的大规模基准测试中，SurvivalPFN表现出色，常优于已有生存模型。结果表明，SurvivalPFN为生存分析提供了一个原则性且实用的基础模型，具有在医疗、金融、工程等高影响力领域的潜在应用价值。
原文摘要 · Abstract (English)
Survival analysis provides a powerful statistical framework for modeling time-to-event outcomes in the presence of censoring. However, selecting an appropriate estimator from the many specialized survival approaches often requires substantial methodological and domain expertise. We introduce SurvivalPFN, a prior-data fitted network that amortizes Bayesian inference for censored observations through in-context learning. SurvivalPFN is pretrained on a diverse family of synthetic, identifiable, and right-censored data-generating processes, enabling it to amortize survival analysis in a single forward pass during inference. As a result, the model adapts to the effective complexity of each dataset without task-specific training or hyperparameter tuning, avoids restrictive parametric assumptions, and produces calibrated survival distributions. In a large-scale benchmark spanning 61 datasets, 21 methods, and 5 evaluation metrics, SurvivalPFN achieves strong predictive performance and often improves upon established survival models. These results suggest that SurvivalPFN offers a principled and practical foundation model for survival analysis, with potential applications in high-impact domains such as healthcare, finance, and engineering (https://github.com/rgklab/SurvivalPFN).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。