Explicitly Modeling Censoring Produces Superior Survival Predictors

Likelihood-based training is the dominant paradigm in survival prediction. Under independent censoring, we can factorize the likelihood and optimize only the terms related to event modeling, effectively treating the censoring mechanism as incidental. This is justified when censoring is non-informative, i.e., when the censoring process shares no parameters with the event-time model. However, this may not hold in practice, and ignoring censoring contributions may discard useful signals for learning representations that can help to effectively estimate event distributions. Motivated by this, we argue that explicitly modeling censoring can improve representation learning and time-to-event estimation, particularly when event and censoring processes are coupled. We introduce a latent decomposition view in which observed covariates are mapped to latent components corresponding to event-specific, censoring-specific, confounding, and irrelevant information. We then learn decomposed representations for the first three categories to guide a better estimation of the event distribution. We instantiate our method on 4 popular deep-learning survival models and evaluate on 10 datasets (2 semi-synthetic and 8 real-world), showing consistent gains over strong baselines and multiple SOTA methods.

Predicting when an important event will happen, such as disease relapse, death, or machine failure, is difficult because many real-world records are incomplete (censored). Most existing methods treat this incompleteness as a nuisance, but it can actually contain useful information about the event we want to predict. We propose SALaD, a method that explicitly learns from both the event process and the incompleteness process, while separating the information that is useful for each. Across 10 survival prediction datasets, SALaD improves prediction accuracy over strong existing methods, which could support more reliable decision-making in healthcare and other time-to-event applications.