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 2004.13303cs.LGstat.ML
收藏

异质性表示学习研究综述

Heterogeneous Representation Learning: A Review

IHPC, A*STAR(新加坡科技研究局高性能计算研究所);College of Computer Science, Sichuan University(四川大学计算机学院);Nanyang Technology University(南洋理工大学)

Joey Tianyi Zhou, Xi Peng, Yew-Soon Ong

摘要:

现实世界中的数据通常具有模态、视图或资源等异构特性,这给数据挖掘带来了一些独特的挑战,其中异构表示学习(HRL)是本文提出的一个关键问题。这个简短的调查涵盖了HRL的主题,围绕着几个主要的学习环境和现实世界的应用。首先,从数学的角度,我们提出了一个统一的学习框架,它能够模拟大多数现有的学习设置与异构输入。在此基础上,我们从数学的角度对HRL框架进行了全面的讨论,包括多视角学习、异构迁移学习、利用特权信息的学习和异构多任务学习。对于每个学习任务,我们还讨论了这些学习问题下的一些应用,并举例说明了数学框架中的术语。最后,我们强调了在HRL中较少触及的挑战,并提出了未来的研究方向。据我们所知,现时并没有这样的架构,可以把这些不同的问题统一起来,而这项调查会令社会得益。

英文摘要:

The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper. This brief survey covers the topic of HRL, centered around several major learning settings and real-world applications. First of all, from the mathematical perspective, we present a unified learning framework which is able to model most existing learning settings with the heterogeneous inputs. After that, we conduct a comprehensive discussion on the HRL framework by reviewing some selected learning problems along with the mathematics perspectives, including multi-view learning, heterogeneous transfer learning, Learning using privileged information and heterogeneous multi-task learning. For each learning task, we also discuss some applications under these learning problems and instantiates the terms in the mathematical framework. Finally, we highlight the challenges that are less-touched in HRL and present future research directions. To the best of our knowledge, there is no such framework to unify these heterogeneous problems, and this survey would benefit the community.

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。

↑