A Survey on Multi-Task Learning

TL;DR

This survey comprehensively reviews multi-task learning (MTL), covering algorithmic approaches, applications, theoretical insights, and future directions, highlighting its role in improving generalization across related tasks.

Contribution

It provides a systematic classification of MTL algorithms, discusses integration with other paradigms, and reviews recent advances in large-scale and high-dimensional settings.

Findings

Classified MTL algorithms into five categories.

Reviewed MTL applications in various domains.

Discussed theoretical analyses and future research directions.

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.