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.

Enhanced matrix inference with Seq2seq models via diagonal sorting

“…The permutation invariance in set-to-sequence paradigm provides inspiration for proposing mapping invariance in this study. With the set-to-sequence approach, the input consists of an unordered collection of elements, while the output is an ordered sequence 19 . Unlike the widely used seq2seq method, the set-to-sequence approach needs to address the appropriate representation of the input set, given its unordered nature.…”

Методы Прогнозирования В Машинном Обучении: Обзор И Сравнение

“…Приложения которой варьируются от языкового моделирования и мета-обучения до многоагентных стратегических игр и оптимизации электросетей. Сочетая элементы обучения представлению и структурированного прогнозирования, его две основные задачи включают в себя получение значимого представления множества, инвариантного к перестановкам , и последующее использование этого представления для вывода сложной целевой перестановки [4].…”

Set Interdependence Transformer: Set-to-Sequence Neural Networks for Permutation Learning and Structure Prediction

“…form of sentence and paragraph ordering [Wang and Wan, 2019;Pandey and Chowdary, 2020], text comprehension [Li and Gao, 2020] and discourse coherence maximization [Farag, 2021]; computer vision for relative attribute learning [Santa Cruz and Fernando, 2017] and rigid point cloud registration [Yew and Lee, 2020]; reinforcement learning for managing the combinatorial action space of an agent [Vinyals et al, 2019]. For an overview, see Jurewicz and Derczynski (2021b). We adapt our method to a novel application domain in the form of predicting the structure of digital catalogs.…”