A Survey on Hypergraph Neural Networks: An In-Depth and Step-By-Step Guide

TL;DR

This survey provides a comprehensive overview of hypergraph neural networks (HNNs), detailing their architectures, training methods, and applications across various fields, highlighting recent advances and future challenges.

Contribution

It is the first detailed survey on HNNs, systematically analyzing their design components, learning mechanisms, and diverse applications in a step-by-step manner.

Findings

HNN architectures are composed of four key design components.

HNNs effectively model higher-order interactions in complex systems.

Applications of HNNs span recommendation systems, bioinformatics, time series, and computer vision.

Abstract

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.