mlsanityData to 7 Oct 2026

Hyperbolic Graph Neural Networks

arXiv 1910.12892 ↗First posted 28 Oct 2019cs.LG stat.MLcited by 244

Not on the map. Why?

Abstract (arXiv)

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we propose a novel GNN architecture for learning representations on Riemannian manifolds with differentiable exponential and logarithmic maps. We develop a scalable algorithm for modeling the structural properties of graphs, comparing Euclidean and hyperbolic geometry. In our experiments, we show that hyperbolic GNNs can lead to substantial improvements on various benchmark datasets.

Key facts. Cited by 244 papers in the map (data through 7 Oct 2026). First posted on arXiv 28 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 39; 2022: 35; 2023: 53; 2024: 33; 2025: 46; 2026: 38.

244 papers.

Sort:

By area:

  1. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 471
  2. 2022Graph neural networks for materials science and chemistrycited by 181
  3. 2023A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detectioncited by 145
  4. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  5. 2021Fully Hyperbolic Neural Networkscited by 107
  6. 2022Hyperbolic Image Segmentationcited by 101
  7. 2021Beltrami Flow and Neural Diffusion on Graphscited by 84
  8. 2021Size-Invariant Graph Representations for Graph Classification Extrapolationscited by 82
  9. 2022When Do Flat Minima Optimizers Work?cited by 78
  10. 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
  11. 2023Hyperbolic Deep Learning in Computer Vision: A Surveycited by 72
  12. 2024Compositional Entailment Learning for Hyperbolic Vision-Language Modelscited by 72
38 more
  1. 2023GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learningcited by 70
  2. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  3. 2021Lorentzian Graph Convolutional Networkscited by 66
  4. 2022Hyperbolic Contrastive Learning for Visual Representations beyond Objectscited by 58
  5. 2021Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifierscited by 56
  6. 2021A Hyperbolic-to-Hyperbolic Graph Convolutional Networkcited by 53
  7. 2021Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threadscited by 51
  8. 2021Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphscited by 49
  9. 2021Learning the Predictability of the Futurecited by 48
  10. 2021HoroPCA: Hyperbolic Dimensionality Reduction via Horospherical Projectionscited by 47
  11. 2023HYperbolic Self-Paced Learning for Self-Supervised Skeleton-based Action Representationscited by 42
  12. 2021Hyperbolic Busemann Learning with Ideal Prototypescited by 40
  13. 2022Hyperbolic Graph Neural Networks: A Review of Methods and Applicationscited by 40
  14. 2024Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Spacecited by 39
  15. 2022HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularizationcited by 34
  16. 2021A Self-supervised Mixed-curvature Graph Neural Networkcited by 32
  17. 2022Self-Supervised Continual Graph Learning in Adaptive Riemannian Spacescited by 32
  18. 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometrycited by 32
  19. 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
  20. 2021CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Datacited by 28
  21. 2021Where are we in embedding spaces? A Comprehensive Analysis on Network Embedding Approaches for Recommender Systemscited by 24
  22. 2021ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Networkcited by 24
  23. 2022HICF: Hyperbolic Informative Collaborative Filteringcited by 24
  24. 2022A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learningcited by 24
  25. 2023Poincar'e ResNetcited by 24
  26. 2024Hyperbolic Fine-Tuning for Large Language Modelscited by 24
  27. 2021Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspectivecited by 23
  28. 2022Heterogeneous manifolds for curvature-aware graph embeddingcited by 23
  29. 2022Latent Graph Inference using Product Manifoldscited by 23
  30. 2024Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learningcited by 23
  31. 2022Graph Neural Networks Designed for Different Graph Types: A Surveycited by 21
  32. 2023A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifoldcited by 21
  33. 2023Hyperbolic Representation Learning: Revisiting and Advancingcited by 21
  34. 2025Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generationcited by 21
  35. 2022Enhancing Hyperbolic Graph Embeddings via Contrastive Learningcited by 20
  36. 2024Hyperbolic Geometric Latent Diffusion Model for Graph Generationcited by 20
  37. 2025Hyperbolic Category Discoverycited by 20
  38. 2025Hyperbolic Deep Learning for Foundation Models: A Surveycited by 20

50 most cited of 244 All 244 (JSON)