Differentiable sorting for censored time-to-event data.
Keywords: Survival Analysis, Censored Data, Semi-supervised Learning, Time-to-event-data, Algorithmic Supervision, Sorting, Risk Prediction, Weakly-supervised Learning, Machine Learning, Cox's Partial Likelihood, Differentiable Sorting Networks, Transitive Inductive Bias, Ranking Losses, Listwise Ranking, Healthcare Applications, Deep Learning, Neural Networks, Top-k Risk Prediction
TL;DR: Diffsurv introduces a novel extension of differentiable sorting methods to survival analysis, effectively handling censored data.
Abstract: Survival analysis is a crucial semi-supervised task in machine learning with significant real-world applications, especially in healthcare. The most common approach to survival analysis, Cox’s partial likelihood, can be interpreted as a ranking model optimized on a lower bound of the concordance index. We follow these connections further, with listwise ranking losses that allow for a relaxation of the pairwise independence assumption. Given the inherent transitivity of ranking, we explore differentiable sorting networks as a means to introduce a stronger transitive inductive bias during optimization. Despite their potential, current differentiable sorting methods cannot account for censoring, a crucial aspect of many real-world datasets. We propose a novel method, Diffsurv, to overcome this limitation by extending differentiable sorting methods to handle censored tasks. Diffsurv predicts matrices of possible permutations that accommodate the label uncertainty introduced by censored samples. Our experiments reveal that Diffsurv outperforms established baselines in various simulated and real-world risk prediction scenarios. Furthermore, we demonstrate the algorithmic advantages of Diffsurv by presenting a novel method for top-k risk prediction that surpasses current methods.
Submission Number: 14596
Loading