Variational Deep Survival Machines: Survival Regression with Censored Outcomes

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Qinxin, Huang, Jiayuan, Li, Junhui, Liu, Jiaming
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909180038742016
author Wang, Qinxin
Huang, Jiayuan
Li, Junhui
Liu, Jiaming
author_facet Wang, Qinxin
Huang, Jiayuan
Li, Junhui
Liu, Jiaming
contents Survival regression aims to predict the time when an event of interest will take place, typically a death or a failure. A fully parametric method [18] is proposed to estimate the survival function as a mixture of individual parametric distributions in the presence of censoring. In this paper, We present a novel method to predict the survival time by better clustering the survival data and combine primitive distributions. We propose two variants of variational auto-encoder (VAE), discrete and continuous, to generate the latent variables for clustering input covariates. The model is trained end to end by jointly optimizing the VAE loss and regression loss. Thorough experiments on dataset SUPPORT and FLCHAIN show that our method can effectively improve the clustering result and reach competitive scores with previous methods. We demonstrate the superior result of our model prediction in the long-term. Our code is available at https://github.com/qinzzz/auton-survival-785.
format Preprint
id arxiv_https___arxiv_org_abs_2404_15595
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Variational Deep Survival Machines: Survival Regression with Censored Outcomes
Wang, Qinxin
Huang, Jiayuan
Li, Junhui
Liu, Jiaming
Machine Learning
Computational Engineering, Finance, and Science
Survival regression aims to predict the time when an event of interest will take place, typically a death or a failure. A fully parametric method [18] is proposed to estimate the survival function as a mixture of individual parametric distributions in the presence of censoring. In this paper, We present a novel method to predict the survival time by better clustering the survival data and combine primitive distributions. We propose two variants of variational auto-encoder (VAE), discrete and continuous, to generate the latent variables for clustering input covariates. The model is trained end to end by jointly optimizing the VAE loss and regression loss. Thorough experiments on dataset SUPPORT and FLCHAIN show that our method can effectively improve the clustering result and reach competitive scores with previous methods. We demonstrate the superior result of our model prediction in the long-term. Our code is available at https://github.com/qinzzz/auton-survival-785.
title Variational Deep Survival Machines: Survival Regression with Censored Outcomes
topic Machine Learning
Computational Engineering, Finance, and Science
url https://arxiv.org/abs/2404.15595