mlsanityData to 7 Oct 2026

Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders

arXiv 2103.16046 ↗First posted 30 Mar 2021cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

Most of the existing literature regarding hyperbolic embedding concentrate upon supervised learning, whereas the use of unsupervised hyperbolic embedding is less well explored. In this paper, we analyze how unsupervised tasks can benefit from learned representations in hyperbolic space. To explore how well the hierarchical structure of unlabeled data can be represented in hyperbolic spaces, we design a novel hyperbolic message passing auto-encoder whose overall auto-encoding is performed in hyperbolic space. The proposed model conducts auto-encoding the networks via fully utilizing hyperbolic geometry in message passing. Through extensive quantitative and qualitative analyses, we validate the properties and benefits of the unsupervised hyperbolic representations. Codes are available at https://github.com/junhocho/HGCAE.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 40 of its 79 references that are in the map. First posted on arXiv 30 Mar 2021.

Builds on

40 of 79 references.

References · 40

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  4. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  5. 2017Graph Attention Networkscited by 8,854
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  12. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
28 more
  1. 2016Variational Graph Auto-Encoderscited by 1,373
  2. 2018Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognitioncited by 1,199
  3. 2015Unsupervised Deep Embedding for Clustering Analysiscited by 763
  4. 2015Image-based Recommendations on Styles and Substitutescited by 702
  5. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 674
  6. 2020Contrastive Learning with Hard Negative Samplescited by 619
  7. 2018Spherical CNNscited by 452
  8. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  9. 2018Hyperbolic Neural Networkscited by 393
  10. 2019On Mutual Information Maximization for Representation Learningcited by 315
  11. 2018Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometrycited by 261
  12. 2019Hyperbolic Graph Neural Networkscited by 244
  13. 2019Hyperbolic Image Embeddingscited by 219
  14. 2016Joint Unsupervised Learning of Deep Representations and Image Clusterscited by 205
  15. 2018Representation Tradeoffs for Hyperbolic Embeddingscited by 204
  16. 2018Riemannian Adaptive Optimization Methodscited by 187
  17. 2018Hyperbolic Attention Networkscited by 122
  18. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 111
  19. 2019Constant Curvature Graph Convolutional Networkscited by 106
  20. 2019Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learningcited by 94
  21. 2019Mixed-curvature Variational Autoencoderscited by 85
  22. 2018Adversarially Regularized Graph Autoencoder for Graph Embeddingcited by 84
  23. 2019Deep Comprehensive Correlation Mining for Image Clusteringcited by 80
  24. 2019Deep Discriminative Clustering Analysiscited by 28
  25. 2015Stacked What-Where Auto-encoderscited by 20
  26. 2019Anchor Loss: Modulating Loss Scale based on Prediction Difficultycited by 14
  27. 2019Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learningcited by 13
  28. 2018Adversarial Autoencoders with Constant-Curvature Latent Manifoldscited by 12

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 4; 2023: 4; 2024: 4; 2025: 2.

15 papers.

Sort:

By area:

  1. 2022Hyperbolic Contrastive Learning for Visual Representations beyond Objectscited by 58
  2. 2022The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generationcited by 22
  3. 2023Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Reviewcited by 20
  4. 2021Graph Neural Networks: Methods, Applications, and Opportunitiescited by 16
  5. 2022Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical Projectionscited by 16
  6. 2022Curved Geometric Networks for Visual Anomaly Recognitioncited by 15
  7. 2023Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detectioncited by 14
  8. 2023Hyperbolic Graph Diffusion Modelcited by 6
  9. 2023Relating tSNE and UMAP to Classical Dimensionality Reductioncited by 3
  10. 2024Hyperbolic Metric Learning for Visual Outlier Detectioncited by 3
  11. 2024HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generationcited by 3
  12. 2024Seg-HGNN: Unsupervised and Light-Weight Image Segmentation with Hyperbolic Graph Neural Networkscited by 0
3 more
  1. 2024Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Spacecited by 0
  2. 2025Breaking the Euclidean Barrier: Hyperboloid-Based Biological Sequence Analysiscited by 0
  3. 2025Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detectioncited by 0