A Survey on Multi-Task Learning

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.

1 Introduction

Human can learn multiple tasks simultaneously and during this learning process, human can use the knowledge learned in a task to help the learning of another task. For example, according to our experience in learning to play tennis and squash, we find that the skill of playing tennis can help learn to play squash and vice versa. Inspired by such human learning ability, Multi-Task Learning (MTL) [1], a learning paradigm in machine learning, aims to learn multiple related tasks jointly so that the knowledge contained in a task can be leveraged by other tasks, with the hope of improving the generalization performance of all the tasks at hand.