An overview of multi-task learning

TLDR

Multi‑task learning is a promising machine‑learning approach that improves performance across related tasks by sharing information, and it is applied in domains such as computer vision, bioinformatics, health informatics, speech, natural language processing, web applications, and ubiquitous computing. This paper provides an overview of multi‑task learning, beginning with a definition of the concept. The authors describe various MTL settings—supervised, unsupervised, semi‑supervised, active, reinforcement, online, and multi‑view—present representative models for each, discuss parallel and distributed variants, and review recent theoretical analyses. The review highlights that MTL has been successfully applied to improve performance in many application areas, with representative works discussed.

Abstract

Abstract As a promising area in machine learning, multi-task learning (MTL) aims to improve the performance of multiple related learning tasks by leveraging useful information among them. In this paper, we give an overview of MTL by first giving a definition of MTL. Then several different settings of MTL are introduced, including multi-task supervised learning, multi-task unsupervised learning, multi-task semi-supervised learning, multi-task active learning, multi-task reinforcement learning, multi-task online learning and multi-task multi-view learning. For each setting, representative MTL models are presented. In order to speed up the learning process, parallel and distributed MTL models are introduced. Many areas, including computer vision, bioinformatics, health informatics, speech, natural language processing, web applications and ubiquitous computing, use MTL to improve the performance of the applications involved and some representative works are reviewed. Finally, recent theoretical analyses for MTL are presented.