A Survey on Multi-Task Learning
Authors:
Top Cited Papers
- 31 March 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (12) , 5586-5609
Abstract
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL from the perspective of algorithmic modeling, applications and theoretical analyses. For algorithmic modeling, we give a definition of MTL and then classify different MTL algorithms into five categories, including feature learning approach, low-rank approach, task clustering approach, task relation learning approach and decomposition approach as well as discussing the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, unsupervised learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, we review online, parallel and distributed MTL models as well as dimensionality reduction and feature hashing to reveal their computational and storage advantages. Many real-world applications use MTL to boost their performance and we review representative works in this paper. Finally, we present theoretical analyses and discuss several future directions for MTL.Keywords
Funding Information
- NSFC (62076118)
This publication has 130 references indexed in Scilit:
- Multitask learning for host–pathogen protein interactionsBioinformatics, 2013
- ProDiGe: Prioritization Of Disease Genes with multitask machine learning from positive and unlabeled examplesBMC Bioinformatics, 2011
- Support union recovery in high-dimensional multivariate regressionThe Annals of Statistics, 2011
- Inferring latent task structure for Multitask Learning by Multiple Kernel LearningBMC Bioinformatics, 2010
- Semi-supervised multi-task learning for predicting interactions between HIV-1 and human proteinsBioinformatics, 2010
- Multi-population GWA mapping via multi-task regularized regressionBioinformatics, 2010
- Sparse multitask regression for identifying common mechanism of response to therapeutic targetsBioinformatics, 2010
- Multi-task learning for cross-platform siRNA efficacy prediction: an in-silico studyBMC Bioinformatics, 2010
- Trace Norm Regularization: Reformulations, Algorithms, and Multi-Task LearningSIAM Journal on Optimization, 2010
- Inductive transfer with context-sensitive neural networksMachine Learning, 2008