A Multi-Task Learning Formulation for Survival Analysis

By Yan Li, Jie Wang, Jieping Ye, Chandan K. Reddy. 2016

138 citations recorded by the source corpus.

Predicting the occurrence of a particular event of interest at future time points is the primary goal of survival analysis. The presence of incomplete observations due to time limitations or loss of data traces is known as censoring which brings unique challenges in this domain and differentiates survival analysis from other standard regression methods. The popularly used survival analysis methods such as Cox proportional hazard model and parametric survival regression suffer from some strict assumptions and hypotheses that are not realistic in most of the real-world applications. To overcome the weaknesses of these two types of methods, in this paper, we reformulate the survival analysis problem as a multi-task learning problem and propose a new multi-task learning based formulation to predict the survival time by estimating the survival status at each time interval during the study duration. We propose an indicator matrix to enable the multi-task learning algorithm to handle censored instances and incorporate some of the important characteristics of survival problems such as non-negative non-increasing list structure into our model through max-heap projection. We employ the L2,1-norm penalty which enables the model to learn a shared representation across related tasks and hence select important features and alleviate over-fitting in high-dimensional feature spaces; thus, reducing the prediction error of each task. To efficiently handle the two non-smooth constraints, in this paper, we propose an optimization method which employs Alternating Direction Method of Multipliers (ADMM) algorithm to solve the proposed multi-task learning problem. We demonstrate the performance of the proposed method using real-world microarray gene expression high-dimensional benchmark datasets and show that our method outperforms state-of-the-art methods.

Subfields: Artificial Intelligence, Statistics and Probability, Representation & Self-Supervised Learning, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Qiang Yang
3. Yu Zhang
4. Xinchao Wang
5. Mingli Song
6. Junzhou Huang
7. Chandan K. Reddy
8. Ping Wang

In Statistics and Probability

1. Qiang Yang
2. Yu Zhang
3. Dacheng Tao
4. Chandan K. Reddy
5. Junzhou Huang
6. Yan Li
7. Ping Wang
8. Kengo Kato

In Representation & Self-Supervised Learning

1. Qiang Yang
2. Yu Zhang
3. Dacheng Tao
4. Ping Wang
5. Chandan K. Reddy
6. Yan Li
7. Junzhou Huang
8. Mingli Song

In Medical & Health AI

1. Qiang Yang
2. Yu Zhang
3. Dacheng Tao

Citations in the corpus

• An Overview of Multi-task Learning (2018, background): “…in Alzheimer’s disease [109], identification of longitudinal phenotypic markers for Alzheimer’s disease progression prediction [110], prioritization of disease genes [111], biological image analysis based on natural images [20], survival analysis [112], and multiple genetic trait prediction [113].”
• A Survey on Multi-Task Learning (2017, methodology): “In [193], the survival analysis problem is formulated as a multi-task classifi-”
• Whole slide images based cancer survival prediction using attention guided deep multiple instance learning networks (2020, methodology): “In MCO-130K, around 100 patches per WSI are sampled and it clearly can see that clustering based on A PREPRINT - SEPTEMBER 24, 2020 MCO_1M MCO_130K WSISALassoCox WSISAEnCox WSISAMTLSA C=6 C=8 DeepAttnMISL C=10 C=12 WSISALassoCox WSISAEnCox WSISAMTLSA MCO_1M MCO_130K DeepAttnMISL C=6 C=8 C=10 C=12 MC”
• Amalgamating Knowledge from Heterogeneous Graph Neural Networks (2021, background): “In the past few years, multi-task learning has been widely studied in various areas, such as bioinformatics [10, 20], ubiquitous computing [39, 40], natural language processing [4, 38] and computer vision [21, 54, 15, 14].”
• Machine Learning for Survival Analysis (2019, background): “In recent years, a number of studies (Li et al. 2016d; Beer et al. 2002) have correlated gene expression with survival outcomes for cancer applications at a genome-wide scale.”
• Machine Learning for Survival Analysis: A Survey (2017, background): “In [Li et al. 2016d], the survival time prediction problem is reformulated as a multi-task learning problem.”