# Deep Lifetime Clustering

arXiv: https://arxiv.org/abs/1910.00547 · HTML: https://mlsanity.com/paper/1910.00547/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2019.

## Built on by (most cited first, 4 of 4)

- [Clustering Survival Data using a Mixture of Non-parametric Experts](https://mlsanity.com/paper/2405.15934/) (2024)
- [Multi-Source Survival Domain Adaptation](https://mlsanity.com/paper/2212.00424/) (2022)
- [Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence](https://mlsanity.com/paper/2506.12944/) (2025)
- [Functional Clustering of Survival Data via Smoothed Log-Hazard Trajectories: A Risk-Dynamics Perspective](https://mlsanity.com/paper/2606.01239/) (2026)

## Abstract (arXiv)

The goal of lifetime clustering is to develop an inductive model that maps subjects into K clusters according to their underlying (unobserved) lifetime distribution. We introduce a neural-network based lifetime clustering model that can find cluster assignments by directly maximizing the divergence between the empirical lifetime distributions of the clusters. Accordingly, we define a novel clustering loss function over the lifetime distributions (of entire clusters) based on a tight upper bound of the two-sample Kuiper test p-value. The resultant model is robust to the modeling issues associated with the unobservability of termination signals, and does not assume proportional hazards. Our results in real and synthetic datasets show significantly better lifetime clusters (as evaluated by C-index, Brier Score, Logrank score and adjusted Rand index) as compared to competing approaches.