mlsanityData to 7 Oct 2026

Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

arXiv 2104.02228 ↗First posted 6 Apr 2021cs.LG cs.SIcited by 49

Not on the map. Why?

Abstract (arXiv)

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representation in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN. Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets.

Key facts. Cited by 49 papers in the map (data through 7 Oct 2026). Builds on 24 of its 46 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

24 of 46 references.

References · 24

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  6. 2016Variational Graph Auto-Encoderscited by 1,373
  7. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  8. 2015LINE: Large-scale Information Network Embeddingcited by 582
  9. 2020Inductive Representation Learning on Temporal Graphscited by 454
  10. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  11. 2019Predicting Dynamic Embedding Trajectory in Temporal Interaction Networkscited by 443
  12. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
12 more
  1. 2018Hyperbolic Neural Networkscited by 393
  2. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  3. 2019Hyperbolic Graph Neural Networkscited by 244
  4. 2018Poincar'e GloVe: Hyperbolic Word Embeddingscited by 155
  5. 2019Multi-relational Poincar'e Graph Embeddingscited by 126
  6. 2018Hyperbolic Attention Networkscited by 122
  7. 2019Continuous Graph Neural Networkscited by 114
  8. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 111
  9. 2019Variational Graph Recurrent Neural Networkscited by 86
  10. 2019Hierarchical Taxonomy-Aware and Attentional Graph Capsule RCNNs for Large-Scale Multi-Label Text Classificationcited by 31
  11. 2017Hyperbolic Representation Learning for Fast and Efficient Neural Question Answeringcited by 23
  12. 2019DNA: Dynamic Social Network Alignmentcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 11; 2023: 9; 2024: 14; 2025: 9; 2026: 3.

49 papers.

Sort:

By area:

  1. 2022Hyperbolic Graph Neural Networks: A Review of Methods and Applicationscited by 40
  2. 2023LLM4DyG: Can Large Language Models Solve Spatial-Temporal Problems on Dynamic Graphs?cited by 40
  3. 2021A Self-supervised Mixed-curvature Graph Neural Networkcited by 32
  4. 2022Self-Supervised Continual Graph Learning in Adaptive Riemannian Spacescited by 32
  5. 2025RiemannGFM: Learning a Graph Foundation Model from Riemannian Geometrycited by 32
  6. 2021ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Networkcited by 24
  7. 2022A Self-supervised Riemannian GNN with Time Varying Curvature for Temporal Graph Learningcited by 24
  8. 2024Motif-aware Riemannian Graph Neural Network with Generative-Contrastive Learningcited by 23
  9. 2022Graph Neural Networks Designed for Different Graph Types: A Surveycited by 21
  10. 2023Hyperbolic Representation Learning: Revisiting and Advancingcited by 21
  11. 2024Uncertainty in Graph Neural Networks: A Surveycited by 20
  12. 2024Hyperbolic Geometric Latent Diffusion Model for Graph Generationcited by 20
37 more
  1. 2024LSEnet: Lorentz Structural Entropy Neural Network for Deep Graph Clusteringcited by 20
  2. 2024Spectral Invariant Learning for Dynamic Graphs under Distribution Shiftscited by 18
  3. 2023Contrastive Graph Clustering in Curvature Spacescited by 15
  4. 2024DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashingcited by 15
  5. 2024Spiking Graph Neural Network on Riemannian Manifoldscited by 15
  6. 2023HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Predictioncited by 13
  7. 2024BotDGT: Dynamicity-aware Social Bot Detection with Dynamic Graph Transformerscited by 10
  8. 2022Curvature Graph Generative Adversarial Networkscited by 9
  9. 2023Hyperbolic Random Forestscited by 9
  10. 2022Autoencoding Hyperbolic Representation for Adversarial Generationcited by 7
  11. 2022Variational Graph Generator for Multi-View Graph Clusteringcited by 7
  12. 2022WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users across Networks via Regularized Representation Learningcited by 7
  13. 2025Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Modelscited by 6
  14. 2023Out-of-Distribution Generalized Dynamic Graph Neural Network for Human Albumin Predictioncited by 5
  15. 2025Spectro-Riemannian Graph Neural Networkscited by 5
  16. 2023SINCERE: Sequential Interaction Networks representation learning on Co-Evolving RiEmannian manifoldscited by 4
  17. 2022Towards Scalable Hyperbolic Neural Networks using Taylor Series Approximationscited by 3
  18. 2023Heterogeneous Social Event Detection via Hyperbolic Graph Representationscited by 3
  19. 2024Contrastive Sequential Interaction Network Learning on Co-Evolving Riemannian Spacescited by 3
  20. 2024Uncertainty Quantification on Graph Learning: A Surveycited by 3
  21. 2021Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchorscited by 2
  22. 2022TPGNN: Learning High-order Information in Dynamic Graphs via Temporal Propagationcited by 2
  23. 2022Hyperbolic Graph Representation Learning: A Tutorialcited by 2
  24. 2024RCoCo: Contrastive Collective Link Prediction across Multiplex Network in Riemannian Spacecited by 2
  25. 2024CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Networkcited by 2
  26. 2024R-ODE: Ricci Curvature Tells When You Will be Informedcited by 2
  27. 2025ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learningcited by 2
  28. 2025HyperbolicRAG: Enhancing Retrieval-Augmented Generation with Hyperbolic Representationscited by 2
  29. 2026Heterophily-Agnostic Hypergraph Neural Networks with Riemannian Local Exchangercited by 2
  30. 2023Improving embedding of graphs with missing data by soft manifoldscited by 1
  31. 2024Why are hyperbolic neural networks effective? A study on hierarchical representation capabilitycited by 1
  32. 2025HyPCV-Former: Hyperbolic Spatio-Temporal Transformer for 3D Point Cloud Video Anomaly Detectioncited by 1
  33. 2025Adaptive Riemannian Graph Neural Networkscited by 1
  34. 2026Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switchingcited by 1
  35. 2026Riemannian Geometry Speaks Louder Than Words: From Graph Foundation Model to Next-Generation Graph Intelligencecited by 1
  36. 2025Spectral Contraction of Boundary-Weighted Filters on delta-Hyperbolic Graphscited by 0
  37. 2025Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detectioncited by 0