Tabular Foundation Models Can Do Survival Analysis

• URL: http://arxiv.org/abs/2601.22259v1
• Date: Thu, 29 Jan 2026 19:29:24 GMT
• Title: Tabular Foundation Models Can Do Survival Analysis
• Abstract summary: We develop a classification-based framework that reformulates both static and dynamic survival analysis.<n>Censored observations are naturally handled as examples with missing labels at certain time points.<n>We prove that under standard censoring assumptions, minimizing our binary classification loss recovers the true survival probabilities as the training set size increases.
• Score: 2.9749358564564368
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While tabular foundation models have achieved remarkable success in classification and regression, adapting them to model time-to-event outcomes for survival analysis is non-trivial due to right-censoring, where data observations may end before the event occurs. We develop a classification-based framework that reformulates both static and dynamic survival analysis as a series of binary classification problems by discretizing event times. Censored observations are naturally handled as examples with missing labels at certain time points. This classification formulation enables existing tabular foundation models to perform survival analysis through in-context learning without explicit training. We prove that under standard censoring assumptions, minimizing our binary classification loss recovers the true survival probabilities as the training set size increases. We demonstrate through evaluation across $53$ real-world datasets that off-the-shelf tabular foundation models with this classification formulation outperform classical and deep learning baselines on average over multiple survival metrics.

Related papers

• SurvivalPFN: Amortizing Survival Prediction via In-Context Bayesian Inference [17.180509074623004]
  We introduce SurvivalPFN, a prior-data fitted network that amortizes Bayesian inference for censored observations through in-context learning.<n>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.<n>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.
  arXiv  Detail & Related papers  (2026-05-15T00:13:04Z)
• Survival In-Context: Prior-fitted In-context Learning Tabular Foundation Model for Survival Analysis [19.308150844590916]
  Survival In-Context (SIC) is a prior-fitted in-context learning model for survival analysis.<n>SIC produces individualized survival prediction in a single forward pass.<n>SIC achieves competitive or superior performance compared to classical and deep survival models.
  arXiv  Detail & Related papers  (2026-03-31T09:22:52Z)
• Biased Generalization in Diffusion Models [4.602851365305176]
  Generalization in generative modeling is defined as the ability to learn an underlying distribution from a finite dataset and produce novel samples.<n>In practice, training is often stopped at the minimum of the test loss, taken as an operational indicator of generalization.<n>We challenge this viewpoint by identifying a phase of biased generalization during training, in which the model continues to decrease the test loss while favoring samples with anomalously high proximity to training data.
  arXiv  Detail & Related papers  (2026-03-03T19:25:33Z)
• Understanding Overparametrization in Survival Models through Interpolation [14.444096460952961]
  Recent advances in machine learning have revealed a more complex pattern, textitdouble-descent, in which test loss, after peaking near the threshold, decreases again as model capacity continues to grow.<n>This study investigates overparametrization in four representative survival models: DeepSurv, PC-Hazard, Nnet-Survival, and N-MTLR.
  arXiv  Detail & Related papers  (2025-12-13T21:23:02Z)
• Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
  This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images. We identify model weaknesses by testing the model using the counterfactual image dataset. We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
  arXiv  Detail & Related papers  (2024-06-19T08:07:14Z)
• On Training Survival Models with Scoring Rules [9.330089124239086]
  This work investigates using scoring rules for model training rather than evaluation. We establish a general framework for training survival models that is model agnostic and can learn event time distributions parametrically or non-parametrically. Empirical comparisons on synthetic and real-world data indicate that scoring rules can be successfully incorporated into model training.
  arXiv  Detail & Related papers  (2024-03-19T20:58:38Z)
• Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach [102.0769560460338]
  We develop a simple logits approach (LORT) without the requirement of prior knowledge of the number of samples per class. Our method achieves state-of-the-art performance on various imbalanced datasets, including CIFAR100-LT, ImageNet-LT, and iNaturalist 2018.
  arXiv  Detail & Related papers  (2024-03-01T03:27:08Z)
• Mitigating Catastrophic Forgetting in Task-Incremental Continual Learning with Adaptive Classification Criterion [50.03041373044267]
  We propose a Supervised Contrastive learning framework with adaptive classification criterion for Continual Learning. Experiments show that CFL achieves state-of-the-art performance and has a stronger ability to overcome compared with the classification baselines.
  arXiv  Detail & Related papers  (2023-05-20T19:22:40Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Certifying Data-Bias Robustness in Linear Regression [12.00314910031517]
  We present a technique for certifying whether linear regression models are pointwise-robust to label bias in a training dataset. We show how to solve this problem exactly for individual test points, and provide an approximate but more scalable method. We also unearth gaps in bias-robustness, such as high levels of non-robustness for certain bias assumptions on some datasets.
  arXiv  Detail & Related papers  (2022-06-07T20:47:07Z)
• Flexible Sampling for Long-tailed Skin Lesion Classification [23.185887174849885]
  Existing long-tailed learning methods treat each class equally to re-balance the long-tailed distribution.<n>We propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task.
  arXiv  Detail & Related papers  (2022-04-07T02:13:56Z)
• Smoothed Embeddings for Certified Few-Shot Learning [63.68667303948808]
  We extend randomized smoothing to few-shot learning models that map inputs to normalized embeddings. Our results are confirmed by experiments on different datasets.
  arXiv  Detail & Related papers  (2022-02-02T18:19:04Z)
• Self-Certifying Classification by Linearized Deep Assignment [65.0100925582087]
  We propose a novel class of deep predictors for classifying metric data on graphs within PAC-Bayes risk certification paradigm. Building on the recent PAC-Bayes literature and data-dependent priors, this approach enables learning posterior distributions on the hypothesis space.
  arXiv  Detail & Related papers  (2022-01-26T19:59:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.