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

Mateusz Jurewicz, Leon Derczynski

Research output: Journal Article or Conference Article in JournalJournal articleResearchpeer-review


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.
Original languageEnglish
JournalThe Journal of Artificial Intelligence Research
Pages (from-to)885-924
Publication statusPublished - 12 Aug 2021


Dive into the research topics of 'Set-to-Sequence Methods in Machine Learning: A Review'. Together they form a unique fingerprint.

Cite this