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

Publikation: Artikel i tidsskrift og konference artikel i tidsskriftTidsskriftartikelForskningpeer review

Abstrakt

Machine learning on sets towards sequential output is an important and ubiquitous task, with applications ranging from language modelling 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.
OriginalsprogEngelsk
TidsskriftThe Journal of Artificial Intelligence Research
Vol/bind71
Sider (fra-til)885-924
ISSN1076-9757
DOI
StatusUdgivet - 12 aug. 2021

Fingeraftryk

Dyk ned i forskningsemnerne om 'Set-to-Sequence Methods in Machine Learning: A Review'. Sammen danner de et unikt fingeraftryk.

Citationsformater