A Survey on Multi-Task Learning
Yu Zhang and Qiang Yang Y. Zhang is with Department of Computer Science and Engineering, Southern University of Science and Technology and Peng Cheng Laboratory. Q. Yang is with the Department of Computer Science and Engineering, Hong Kong University of Science and Technology. E-mail: Corresponding author: Yu Zhang.
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 thei
中文速览
多任务学习（Multi-Task Learning, MTL）试图解决的核心问题是：如何让多个相关任务在联合训练中相互借力，从而提升每个任务的泛化性能，尤其是在单任务数据稀缺时效果更为明显。这篇综述从算法建模、实际应用和理论分析三个维度对MTL领域进行了系统梳理，将现有算法归纳为特征学习、低秩、任务聚类、任务关系学习和分解五大类，并详细讨论了MTL与半监督学习、强化学习、多视图学习等范式的结合方式，以及在数据量大或维度高时的在线、并行、分布式解决方案。综述还覆盖了MTL在计算机视觉、生物信息学、自然语言处理等众多领域的代表性应用，并对相关理论成果进行了梳理。这项工作为研究者提供了一张全面的MTL知识地图，有助于快速把握该领域的发展脉络、方法边界与未来方向。
原文 arXiv:1707.08114;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1707.08114v3