mlsanityData to 14 Oct 2026

Learning Hierarchical Priors in VAEs

arXiv 1905.04982 ↗First posted 13 May 2019stat.ML cs.LGcited by 53

Not on the map. Why?

Abstract (arXiv)

We propose to learn a hierarchical prior in the context of variational autoencoders to avoid the over-regularisation resulting from a standard normal prior distribution. To incentivise an informative latent representation of the data, we formulate the learning problem as a constrained optimisation problem by extending the Taming VAEs framework to two-level hierarchical models. We introduce a graph-based interpolation method, which shows that the topology of the learned latent representation corresponds to the topology of the data manifold---and present several examples, where desired properties of latent representation such as smoothness and simple explanatory factors are learned by the prior.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 13; 2023: 11; 2024: 10; 2025: 4; 2026: 4.

53 papers.

Sort:

By area:

  1. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  2. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  3. 2022Efficient-VDVAE: Less is morecited by 26
  4. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  5. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  6. 2024You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANscited by 26
  7. 2021Conditional Image Generation by Conditioning Variational Auto-Encoderscited by 25
  8. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  9. 2021Multiresolution Equivariant Graph Variational Autoencodercited by 20
  10. 2022Fuse It More Deeply! A Variational Transformer with Layer-Wise Latent Variable Inference for Text Generationcited by 20
  11. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  12. 2021Mind the Gap when Conditioning Amortised Inference in Sequential Latent-Variable Modelscited by 14
38 more
  1. 2021A prior-based approximate latent Riemannian metriccited by 11
  2. 2021On Incorporating Inductive Biases into VAEscited by 11
  3. 2023Revisiting Structured Variational Autoencoderscited by 11
  4. 2023Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segmentscited by 11
  5. 2021Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learningcited by 10
  6. 2023VTAE: Variational Transformer Autoencoder with Manifolds Learningcited by 10
  7. 2023Tree Variational Autoencoderscited by 10
  8. 2023Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Predictioncited by 10
  9. 2024Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approachcited by 9
  10. 2024Combining Hierachical VAEs with LLMs for clinically meaningful timeline summarisation in social mediacited by 8
  11. 2024Hierarchical VAE with a Diffusion-based VampPriorcited by 8
  12. 2021Multi-Task Neural Processescited by 7
  13. 2024Counterfactual Concept Bottleneck Modelscited by 7
  14. 2023eVAE: Evolutionary Variational Autoencodercited by 6
  15. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  16. 2021Disentangling Generative Factors of Physical Fields Using Variational Autoencoderscited by 5
  17. 2023Towards Flexibility and Interpretability of Gaussian Process State-Space Modelcited by 5
  18. 2023Variational Mixture of HyperGenerators for Learning Distributions Over Functionscited by 5
  19. 2023One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Modelscited by 4
  20. 2021Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalizationcited by 3
  21. 2022Improving Variational Autoencoders with Density Gap-based Regularizationcited by 3
  22. 2022Multimodal hierarchical Variational AutoEncoders with Factor Analysis latent spacecited by 2
  23. 2025Learning Energy-based Variational Latent Prior for VAEscited by 2
  24. 2026Latent Matters: Learning Deep State-Space Modelscited by 2
  25. 2022Deep clustering with fusion autoencodercited by 1
  26. 2022Flat Latent Manifolds for Human-machine Co-creation of Musiccited by 1
  27. 2022Structured Graph Variational Autoencoders for Indoor Furniture layout Generationcited by 1
  28. 2022Local Distance Preserving Auto-encoders using Continuous k-Nearest Neighbours Graphscited by 1
  29. 2024Guided Decoding for Robot On-line Motion Generation and Adaptioncited by 1
  30. 2021Symmetric Wasserstein Autoencoderscited by 0
  31. 2023Dior-CVAE: Pre-trained Language Models and Diffusion Priors for Variational Dialog Generationcited by 0
  32. 2023Learning variational autoencoders via MCMC speed measurescited by 0
  33. 2024Sequential Model for Predicting Patient Adherence in Subcutaneous Immunotherapy for Allergic Rhinitiscited by 0
  34. 2024Integrative Variational Autoencoders for Generative Modeling of an Image Outcome with Multiple Input Imagescited by 0
  35. 2024M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Schedulingcited by 0
  36. 2025A Generative Deep Learning Workflow for Inverse Molecular Design of Fuelscited by 0
  37. 2025Why Are Parsing Actions for Understanding Message Hierarchies Not Random?cited by 0
  38. 2025Disentangled representations via score-based variational autoencoderscited by 0

50 most cited of 53 All 53 (JSON)