Set-to-Sequence Methods in Machine Learning: a Review
It provides a comprehensive overview for researchers and practitioners working on applications like language modeling and multi-agent systems, but it is incremental as it reviews existing methods.
This paper reviews machine learning methods for set-to-sequence tasks, addressing challenges in permutation invariant set representation and generating target permutations, with a qualitative comparison of model architectures.
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.