arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.09656cs.LGcs.AI
收藏

机器学习中的集合序列方法

Set-to-Sequence Methods in Machine Learning: a Review

IT University of Copenhagen(哥本哈根信息技术大学);Tjek A/S(Tjek公司)

Mateusz Jurewicz, Leon Strømberg-Derczynski

摘要:

面向顺序输出的集合上的机器学习是一项重要且普遍存在的任务,其应用范围从语言建模和元学习到多智能体策略游戏和电网优化。结合表示学习和结构化预测的元素,其两个主要挑战包括获得有意义的置换不变集表示,并随后利用该表示输出复杂的目标置换。本文对该领域进行了全面介绍,并概述了解决这两个关键挑战的重要机器学习方法,并对选定的模型架构进行了详细的定性比较。

英文摘要:

Machine learning on sets towards sequential output is an important and ubiquitous task, with applications ranging from language modeling and meta-learning to multi-agent strategy games and power grid optimization. Combining elements of representation learning and structured prediction, its two primary challenges include obtaining a meaningful, permutation invariant set representation and subsequently utilizing this representation to output a complex target permutation. This paper provides a comprehensive introduction to the field as well as an overview of important machine learning methods tackling both of these key challenges, with a detailed qualitative comparison of selected model architectures.

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。

↑