mlsanityData to 7 Oct 2026

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

arXiv 2404.01039 ↗First posted 1 Apr 2024cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 77 of its 160 references that are in the map. First posted on arXiv 1 Apr 2024.

Builds on

77 of 160 references.

References · 77

  1. 2017Attention Is All You Needcited by 59,932
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  5. 2016Layer Normalizationcited by 5,579
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  7. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  8. 2019Simplifying Graph Convolutional Networkscited by 1,470
  9. 2016Variational Graph Auto-Encoderscited by 1,373
  10. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  11. 2020Graph Contrastive Learning with Augmentationscited by 1,203
  12. 2018Deep Graph Infomaxcited by 1,101
38 more
  1. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  2. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  3. 2018Link Prediction Based on Graph Neural Networkscited by 829
  4. 2020A Survey on Contrastive Self-supervised Learningcited by 553
  5. 2018Hypergraph Neural Networkscited by 482
  6. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 461
  7. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 326
  8. 2021Graph Self-Supervised Learning: A Surveycited by 289
  9. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  10. 2019Hypergraph Convolution and Hypergraph Attentioncited by 226
  11. 2021Identity-aware Graph Neural Networkscited by 197
  12. 2019Universal Invariant and Equivariant Graph Neural Networkscited by 182
  13. 2019On the Universality of Invariant Networkscited by 151
  14. 2020Networks beyond pairwise interactions: structure and dynamicscited by 127
  15. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 127
  16. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 124
  17. 2021SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networkscited by 108
  18. 2020HNHN: Hypergraph Networks with Hyperedge Neuronscited by 104
  19. 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 95
  20. 2020Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendationcited by 75
  21. 2019Hyper-SAGNN: a self-attention based graph neural network for hypergraphscited by 69
  22. 2021What are higher-order networks?cited by 66
  23. 2024Position: Topological Deep Learning is the New Frontier for Relational Learningcited by 65
  24. 2021Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identificationcited by 63
  25. 2021The physics of higher-order interactions in complex systemscited by 63
  26. 2019Random Walks on Hypergraphs with Edge-Dependent Vertex Weightscited by 45
  27. 2023Architectures of Topological Deep Learning: A Survey of Message-Passing Topological Neural Networkscited by 43
  28. 2022Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Predictioncited by 39
  29. 2021Transformers Generalize DeepSets and Can be Extended to Graphs and Hypergraphscited by 35
  30. 2021Double-Scale Self-Supervised Hypergraph Learning for Group Recommendationcited by 32
  31. 2020How Much and When Do We Need Higher-order Information in Hypergraphs? A Case Study on Hyperedge Predictioncited by 31
  32. 2020Structural Patterns and Generative Models of Real-world Hypergraphscited by 29
  33. 2023Towards Deep Attention in Graph Neural Networks: Problems and Remediescited by 24
  34. 2021How Do Hyperedges Overlap in Real-World Hypergraphs? -- Patterns, Measures, and Generatorscited by 22
  35. 2020Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansioncited by 21
  36. 2021Hyperbolic Hypergraphs for Sequential Recommendationcited by 21
  37. 2022I'm Me, We're Us, and I'm Us: Tri-directional Contrastive Learning on Hypergraphscited by 20
  38. 2021Session-based Recommendation with Hypergraph Attention Networkscited by 19

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 9; 2026: 11.

22 papers.

Sort:

  1. 2024Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedycited by 13
  2. 2025Recent Advances in Hypergraph Neural Networkscited by 7
  3. 2025DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learningcited by 5
  4. 2025SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognitioncited by 4
  5. 2024Towards Data-centric Machine Learning on Directed Graphs: a Surveycited by 2
  6. 2026Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchangercited by 2
  7. 2026Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approachcited by 2
  8. 2025Evolving Skeletons: Motion Dynamics in Action Recognitioncited by 1
  9. 2025Learning to Flow from Generative Pretext Tasks for Neural Architecture Encodingcited by 1
  10. 2025Parameter-Free Hypergraph Neural Network for Few-Shot Node Classificationcited by 1
  11. 2026SphUnc: Hyperspherical Uncertainty Decomposition and Causal Identification via Information Geometrycited by 1
  12. 2025Enhancing the Utility of Higher-Order Information in Relational Learningcited by 0
10 more
  1. 2025How Particle System Theory Enhances Hypergraph Message Passingcited by 0
  2. 2025Identifying Group Anchors in Real-World Group Interactions Under Label Scarcitycited by 0
  3. 2026Counterfactual Explanations for Hypergraph Neural Networkscited by 0
  4. 2026Towards Solving Polynomial-Objective Integer Programming with Hypergraph Neural Networkscited by 0
  5. 2026Hypergraph Neural Networks Accelerate MUS Enumerationcited by 0
  6. 2026Hypergraph as Languagecited by 0
  7. 2026Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimationcited by 0
  8. 2026MobileSAM2: Lightweight Segment Anything for Spatial Intelligencecited by 0
  9. 2026Unsupervised Multi-Scale Gromov-Wasserstein Hypergraph Alignmentcited by 0
  10. 2026AutoHGNN: Robust and Efficient Neural Architecture Search for Hypergraph Neural Networkscited by 0