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

Abstract

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 _eld 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.

Cite

Text

Jurewicz and Derczynski. "Set-to-Sequence Methods in Machine Learning: A Review." Journal of Artificial Intelligence Research, 2021. doi:10.1613/JAIR.1.12839

Markdown

[Jurewicz and Derczynski. "Set-to-Sequence Methods in Machine Learning: A Review." Journal of Artificial Intelligence Research, 2021.](https://mlanthology.org/jair/2021/jurewicz2021jair-settosequence/) doi:10.1613/JAIR.1.12839

BibTeX

@article{jurewicz2021jair-settosequence,
  title     = {{Set-to-Sequence Methods in Machine Learning: A Review}},
  author    = {Jurewicz, Mateusz and Derczynski, Leon},
  journal   = {Journal of Artificial Intelligence Research},
  year      = {2021},
  pages     = {885-924},
  doi       = {10.1613/JAIR.1.12839},
  volume    = {71},
  url       = {https://mlanthology.org/jair/2021/jurewicz2021jair-settosequence/}
}