mlsanityData to 7 Oct 2026

Hyperspherical Variational Auto-Encoders

arXiv 1804.00891 ↗First posted 3 Apr 2018stat.ML cs.LGcited by 188

Not on the map. Why?

Abstract (arXiv)

The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or S-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, N-VAE, in low dimensions on other data types. Code at http://github.com/nicola-decao/s-vae-tf and https://github.com/nicola-decao/s-vae-pytorch

Key facts. Cited by 188 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 36; 2022: 33; 2023: 35; 2024: 27; 2025: 27; 2026: 30.

188 papers.

Sort:

By area:

  1. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  2. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  3. 2021Hyperbolic Deep Neural Networks: A Surveycited by 138
  4. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  5. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  6. 2021Learning from Counterfactual Links for Link Predictioncited by 69
  7. 2022SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantizationcited by 68
  8. 2022Unifying Diffusion Models' Latent Space, with Applications to CycleDiffusion and Guidancecited by 67
  9. 2021von Mises-Fisher Loss: An Exploration of Embedding Geometries for Supervised Learningcited by 42
  10. 2022Linkless Link Prediction via Relational Distillationcited by 39
  11. 2023Energy-Based Sliced Wasserstein Distancecited by 39
  12. 2021Learning with Hyperspherical Uniformitycited by 35
38 more
  1. 2022Spherical Sliced-Wassersteincited by 31
  2. 2021Pseudo-Riemannian Graph Convolutional Networkscited by 30
  3. 2023Probabilistic Contrastive Learning Recovers the Correct Aleatoric Uncertainty of Ambiguous Inputscited by 28
  4. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  5. 2021Autoencoding Under Normalization Constraintscited by 26
  6. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  7. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  8. 2021Pulling back information geometrycited by 23
  9. 2021SphereFace Revived: Unifying Hyperspherical Face Recognitioncited by 23
  10. 2021MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retrainingcited by 23
  11. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  12. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  13. 2024Manifold Integrated Gradients: Riemannian Geometry for Feature Attributioncited by 21
  14. 2024Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structurescited by 20
  15. 2022A Non-isotropic Probabilistic Take on Proxy-based Deep Metric Learningcited by 19
  16. 2022Geodesic Graph Neural Network for Efficient Graph Representation Learningcited by 19
  17. 2021Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularizationcited by 17
  18. 2023URL: A Representation Learning Benchmark for Transferable Uncertainty Estimatescited by 17
  19. 2023Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approachcited by 17
  20. 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergencecited by 17
  21. 2022Hyperspherical Consistency Regularizationcited by 16
  22. 2023Manifold Learning by Mixture Models of VAEs for Inverse Problemscited by 16
  23. 2023vONTSS: vMF based semi-supervised neural topic modeling with optimal transportcited by 16
  24. 2025Hyperspherical Latents Improve Continuous-Token Autoregressive Generationcited by 16
  25. 2026Language Modeling with Hyperspherical Flowscited by 15
  26. 2021Addressing the Topological Defects of Disentanglement via Distributed Operatorscited by 14
  27. 2022Hyperbolic VAE via Latent Gaussian Distributionscited by 14
  28. 2026InfoNCE Induces Gaussian Distributioncited by 14
  29. 2021Contrastive Attraction and Contrastive Repulsion for Representation Learningcited by 13
  30. 2023Contracting Skeletal Kinematics for Human-Related Video Anomaly Detectioncited by 13
  31. 2023Pitfalls in Link Prediction with Graph Neural Networks: Understanding the Impact of Target-link Inclusion & Better Practicescited by 13
  32. 2021Dual Metric Learning for Effective and Efficient Cross-Domain Recommendationscited by 12
  33. 2022Continual Learning by Modeling Intra-Class Variationcited by 12
  34. 2023TouchUp-G: Improving Feature Representation through Graph-Centric Finetuningcited by 12
  35. 2024Stereographic Spherical Sliced Wasserstein Distancescited by 12
  36. 2021On Incorporating Inductive Biases into VAEscited by 11
  37. 2023Markovian Sliced Wasserstein Distances: Beyond Independent Projectionscited by 11
  38. 2021Continuous normalizing flows on manifoldscited by 10

50 most cited of 188 All 188 (JSON)