arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1707.08114cs.LGcs.AI
收藏

多任务学习研究综述

A Survey on Multi-Task Learning

Southern University of Science and Technology(南方科技大学);Hong Kong University of Science and Technology(香港科技大学)

Yu Zhang, Qiang Yang

摘要:

多任务学习(MTL)是机器学习中的一种学习范式,其目的是利用多个相关任务中包含的有用信息来帮助提高所有任务的泛化性能。本文从算法建模、应用和理论分析三个方面对多目标线性映射进行了综述。在算法建模方面,首先给出了MTL的定义,然后将MTL算法分为特征学习方法、低秩方法、任务聚类方法、任务关系学习方法和分解方法,并讨论了每种方法的特点。为了进一步提高学习任务的性能,MTL可以与其他学习范式相结合,包括半监督学习,主动学习,无监督学习,强化学习,多视图学习和图形模型。当任务数量很大或数据维数很高时,我们回顾了在线,并行和分布式MTL模型以及降维和特征散列,以揭示其计算和存储优势。许多现实世界中的应用程序使用MTL来提高其性能,我们在本文中审查的代表性工作。最后,我们提出了理论分析,并讨论了几个未来的方向MTL。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑