mlsanityData to 14 Oct 2026

Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection

arXiv 2512.18826 ↗First posted 21 Dec 2025cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

This survey reviews hyperbolic graph embedding models, and evaluate them on anomaly detection, highlighting their advantages over Euclidean methods in capturing complex structures. Evaluating models like textitHGCAE, textit(P)-VAE, and textitHGCN demonstrates high performance, with textit(P)-VAE achieving an F1-score of 94% on the textitElliptic dataset and textitHGCAE scoring 80% on textitCora. In contrast, Euclidean methods like textitDOMINANT and textitGraphSage struggle with complex data. The study emphasizes the potential of hyperbolic spaces for improving anomaly detection, and provides an open-source library to foster further research in this field.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 42 of its 73 references that are in the map. First posted on arXiv 21 Dec 2025.

Builds on

42 of 73 references.

References · 42

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,722
  5. 2016Variational Graph Auto-Encoderscited by 1,382
  6. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  7. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  8. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  9. 2018Hyperbolic Neural Networkscited by 402
  10. 2019Hyperbolic Graph Convolutional Neural Networkscited by 402
  11. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 265
  12. 2017A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applicationscited by 260
30 more
  1. 2019Hyperbolic Graph Neural Networkscited by 244
  2. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 206
  3. 2018Hyperbolic Entailment Cones for Learning Hierarchical Embeddingscited by 162
  4. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  5. 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
  6. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 112
  7. 2019Constant Curvature Graph Convolutional Networkscited by 108
  8. 2019Hyperbolic Graph Attention Networkcited by 70
  9. 2021Lorentzian Graph Convolutional Networkscited by 68
  10. 2021Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Spacecited by 67
  11. 2020Graph Geometry Interaction Learningcited by 55
  12. 2021A Hyperbolic-to-Hyperbolic Graph Convolutional Networkcited by 53
  13. 2021Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphscited by 50
  14. 2020Latent Variable Modelling with Hyperbolic Normalizing Flowscited by 49
  15. 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
  16. 2021ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Networkcited by 25
  17. 2021Symmetric Spaces for Graph Embeddings: A Finsler-Riemannian Approachcited by 23
  18. 2016Machine learning meets network science: dimensionality reduction for fast and efficient embedding of networks in the hyperbolic spacecited by 21
  19. 2019Hyperbolic Disk Embeddings for Directed Acyclic Graphscited by 21
  20. 2021Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoderscited by 15
  21. 2021Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Designcited by 14
  22. 2022kHGCN: Tree-likeness Modeling via Continuous and Discrete Curvature Learningcited by 14
  23. 2023HGWaveNet: A Hyperbolic Graph Neural Network for Temporal Link Predictioncited by 14
  24. 2018Adversarial Autoencoders with Constant-Curvature Latent Manifoldscited by 12
  25. 2019Hydra: A method for strain-minimizing hyperbolic embedding of network- and distance-based datacited by 11
  26. 2019Mercator: uncovering faithful hyperbolic embeddings of complex networkscited by 10
  27. 2015Network Geometry Inference using Common Neighborscited by 8
  28. 2016Embedding Graphs in Lorentzian Spacetimecited by 8
  29. 2019Poincar'e Wasserstein Autoencodercited by 7
  30. 2020Hyperbolic Distance Matricescited by 7

Built on by

Not cited yet.