Saved in:
Bibliographic Details
Main Authors: Kim, Sunwoo, Lee, Soo Yong, Gao, Yue, Antelmi, Alessia, Polato, Mirko, Shin, Kijung
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.01039
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916335791898624
author Kim, Sunwoo
Lee, Soo Yong
Gao, Yue
Antelmi, Alessia
Polato, Mirko
Shin, Kijung
author_facet Kim, Sunwoo
Lee, Soo Yong
Gao, Yue
Antelmi, Alessia
Polato, Mirko
Shin, Kijung
contents Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide. Broadly, the present survey overviews HNN architectures, training strategies, and applications. First, we break existing HNNs down into four design components: (i) input features, (ii) input structures, (iii) message-passing schemes, and (iv) training strategies. Second, we examine how HNNs address and learn HOIs with each of their components. Third, we overview the recent applications of HNNs in recommendation, bioinformatics and medical science, time series analysis, and computer vision. Lastly, we conclude with a discussion on limitations and future directions.
format Preprint
id arxiv_https___arxiv_org_abs_2404_01039
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
Kim, Sunwoo
Lee, Soo Yong
Gao, Yue
Antelmi, Alessia
Polato, Mirko
Shin, Kijung
Machine Learning
Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda for the data mining and machine learning communities. As networks of HOIs are expressed mathematically as hypergraphs, hypergraph neural networks (HNNs) have emerged as a powerful tool for representation learning on hypergraphs. Given the emerging trend, we present the first survey dedicated to HNNs, with an in-depth and step-by-step guide. Broadly, the present survey overviews HNN architectures, training strategies, and applications. First, we break existing HNNs down into four design components: (i) input features, (ii) input structures, (iii) message-passing schemes, and (iv) training strategies. Second, we examine how HNNs address and learn HOIs with each of their components. Third, we overview the recent applications of HNNs in recommendation, bioinformatics and medical science, time series analysis, and computer vision. Lastly, we conclude with a discussion on limitations and future directions.
title A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide
topic Machine Learning
url https://arxiv.org/abs/2404.01039