mlsanityData to 14 Oct 2026

VAE with a VampPrior

arXiv 1705.07120 ↗First posted 19 May 2017cs.LG cs.AI stat.MLcited by 248

Not on the map. Why?

Abstract (arXiv)

Many different methods to train deep generative models have been introduced in the past. In this paper, we propose to extend the variational auto-encoder (VAE) framework with a new type of prior which we call "Variational Mixture of Posteriors" prior, or VampPrior for short. The VampPrior consists of a mixture distribution (e.g., a mixture of Gaussians) with components given by variational posteriors conditioned on learnable pseudo-inputs. We further extend this prior to a two layer hierarchical model and show that this architecture with a coupled prior and posterior, learns significantly better models. The model also avoids the usual local optima issues related to useless latent dimensions that plague VAEs. We provide empirical studies on six datasets, namely, static and binary MNIST, OMNIGLOT, Caltech 101 Silhouettes, Frey Faces and Histopathology patches, and show that applying the hierarchical VampPrior delivers state-of-the-art results on all datasets in the unsupervised permutation invariant setting and the best results or comparable to SOTA methods for the approach with convolutional networks.

Key facts. Cited by 248 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 51; 2022: 50; 2023: 49; 2024: 32; 2025: 34; 2026: 32.

248 papers.

Sort:

By area:

  1. 2021Score-based Generative Modeling in Latent Spacecited by 636
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 553
  3. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 252
  4. 2022A Survey on Generative Diffusion Modelcited by 240
  5. 2023A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPTcited by 224
  6. 2022Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Modelscited by 190
  7. 2021Hyperbolic Deep Neural Networks: A Surveycited by 139
  8. 2022Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functionscited by 133
  9. 2021Image-to-Image Translation: Methods and Applicationscited by 116
  10. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  11. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  12. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
38 more
  1. 2025EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modelingcited by 89
  2. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 80
  3. 2023GIVT: Generative Infinite-Vocabulary Transformerscited by 80
  4. 2022Identifiability of deep generative models without auxiliary informationcited by 70
  5. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  6. 2022Sample-dependent Adaptive Temperature Scaling for Improved Calibrationcited by 48
  7. 2022A Langevin-like Sampler for Discrete Distributionscited by 44
  8. 2022Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoderscited by 42
  9. 2021Contrastively Disentangled Sequential Variational Autoencodercited by 34
  10. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31
  11. 2024Graph Out-of-Distribution Generalization via Causal Interventioncited by 31
  12. 2022Synthetic Data in Human Analysis: A Surveycited by 28
  13. 2021Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencodercited by 27
  14. 2022Particle algorithms for maximum likelihood training of latent variable modelscited by 26
  15. 2022Pythae: Unifying Generative Autoencoders in Python -- A Benchmarking Use Casecited by 26
  16. 2023Future-conditioned Unsupervised Pretraining for Decision Transformercited by 26
  17. 2021Diffusion Priors In Variational Autoencoderscited by 25
  18. 2022A Geometric Perspective on Variational Autoencoderscited by 24
  19. 2021MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retrainingcited by 23
  20. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  21. 2022Representation Uncertainty in Self-Supervised Learning as Variational Inferencecited by 22
  22. 2021Better Latent Spaces for Better Autoencoderscited by 21
  23. 2023The Emergence of Reproducibility and Generalizability in Diffusion Modelscited by 21
  24. 2022On PAC-Bayesian reconstruction guarantees for VAEscited by 20
  25. 2023Learning Manifold Dimensions with Conditional Variational Autoencoderscited by 20
  26. 2022Continuous Mixtures of Tractable Probabilistic Modelscited by 19
  27. 2023Complexity Matters: Rethinking the Latent Space for Generative Modelingcited by 19
  28. 2021Learning Multimodal VAEs through Mutual Supervisioncited by 18
  29. 2022Adaptive Multi-stage Density Ratio Estimation for Learning Latent Space Energy-based Modelcited by 18
  30. 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergencecited by 18
  31. 2021Local Disentanglement in Variational Auto-Encoders Using Jacobian L1 Regularizationcited by 17
  32. 2023Grounded Object Centric Learningcited by 17
  33. 2021Data Augmentation with Variational Autoencoders and Manifold Samplingcited by 16
  34. 2021Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centerscited by 16
  35. 2021Variational Multi-Task Learning with Gumbel-Softmax Priorscited by 15
  36. 2021Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classificationcited by 15
  37. 2024Unity by Diversity: Improved Representation Learning in Multimodal VAEscited by 14
  38. 2021Cauchy-Schwarz Regularized Autoencodercited by 13

50 most cited of 248 All 248 (JSON)