mlsanityData to 7 Oct 2026

Dirichlet Variational Autoencoder

arXiv 1901.02739 ↗First posted 9 Jan 2019cs.LG stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the stochastic gradient method by approximating the Gamma distribution, which is a component of the Dirichlet distribution, with the inverse Gamma CDF approximation. Additionally, we reshape the component collapsing issue by investigating two problem sources, which are decoder weight collapsing and latent value collapsing, and we show that DirVAE has no component collapsing; while Gaussian VAE exhibits the decoder weight collapsing and Stick-Breaking VAE shows the latent value collapsing. The experimental results show that 1) DirVAE models the latent representation result with the best log-likelihood compared to the baselines; and 2) DirVAE produces more interpretable latent values with no collapsing issues which the baseline models suffer from. Also, we show that the learned latent representation from the DirVAE achieves the best classification accuracy in the semi-supervised and the supervised classification tasks on MNIST, OMNIGLOT, and SVHN compared to the baseline VAEs. Finally, we demonstrated that the DirVAE augmented topic models show better performances in most cases.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 9 Jan 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 11; 2022: 10; 2023: 9; 2024: 6; 2025: 7.

43 papers.

Sort:

By area:

  1. 2021Is Automated Topic Model Evaluation Broken?: The Incoherence of Coherencecited by 74
  2. 2021Topic Modelling Meets Deep Neural Networks: A Surveycited by 51
  3. 2023Machine Learning for Anomaly Detection in Particle Physicscited by 29
  4. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  5. 2021Better Latent Spaces for Better Autoencoderscited by 20
  6. 2022Benchmarking Constraint Inference in Inverse Reinforcement Learningcited by 18
  7. 2024A Survey on Neural Topic Models: Methods, Applications, and Challengescited by 18
  8. 2023t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergencecited by 17
  9. 2022SCALE: Online Self-Supervised Lifelong Learning without Prior Knowledgecited by 16
  10. 2021Pathologies in priors and inference for Bayesian transformerscited by 13
  11. 2024Advancing Graph Generation through Beta Diffusioncited by 13
  12. 2023DyGen: Learning from Noisy Labels via Dynamics-Enhanced Generative Modelingcited by 10
31 more
  1. 2024A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challengescited by 10
  2. 2021Generating Multivariate Load States Using a Conditional Variational Autoencodercited by 8
  3. 2023Coupled Variational Autoencodercited by 6
  4. 2022Hyperspectral Pixel Unmixing with Latent Dirichlet Variational Autoencodercited by 5
  5. 2021Online Unsupervised Learning of Visual Representations and Categoriescited by 4
  6. 2022Physics-informed Variational Autoencoders for Improved Robustness to Environmental Factors of Variationcited by 4
  7. 2024Learning Latent Graph Structures and their Uncertaintycited by 4
  8. 2024A Non-negative VAE:the Generalized Gamma Belief Networkcited by 4
  9. 2025Calibrating Pre-trained Language Classifiers on LLM-generated Noisy Labels via Iterative Refinementcited by 4
  10. 2021Hierarchical Variational Auto-Encoding for Unsupervised Domain Generalizationcited by 3
  11. 2022A Prescriptive Dirichlet Power Allocation Policy with Deep Reinforcement Learningcited by 3
  12. 2023Data-driven Nonlinear Parametric Model Order Reduction Framework using Deep Hierarchical Variational Autoencodercited by 3
  13. 2025XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignmentscited by 3
  14. 2022A Framework for Overparameterized Learningcited by 2
  15. 2024Diff-PCC: Diffusion-based Neural Compression for 3D Point Cloudscited by 2
  16. 2025BN-Pool: Bayesian Nonparametric Pooling for Graphscited by 2
  17. 2025Learning Reduced Representations for Quantum Classifierscited by 2
  18. 2021Unsupervised Image Generation with Infinite Generative Adversarial Networkscited by 1
  19. 2022Deep clustering with fusion autoencodercited by 1
  20. 2023Learning disentangled representations for explainable chest X-ray classification using Dirichlet VAEscited by 1
  21. 2023Triggering Dark Showers with Conditional Dual Auto-Encoderscited by 1
  22. 2023A Metalearned Neural Circuit for Nonparametric Bayesian Inferencecited by 1
  23. 2023Variational Autoencoders for Feature Exploration and Malignancy Prediction of Lung Lesionscited by 1
  24. 2021A Deep Latent Space Model for Graph Representation Learningcited by 0
  25. 2021Meta-learning Amidst Heterogeneity and Ambiguitycited by 0
  26. 2021Towards Controllable Agent in MOBA Games with Generative Modelingcited by 0
  27. 2022β-Multivariational Autoencoder for Entangled Representation Learning in Video Framescited by 0
  28. 2022Learning and Predicting Multimodal Vehicle Action Distributions in a Unified Probabilistic Model Without Labelscited by 0
  29. 2025Application of integrated gradients explainability to sociopsychological semantic markerscited by 0
  30. 2025Preference Construction: A Bayesian Interactive Preference Elicitation Framework Based on Monte Carlo Tree Searchcited by 0
  31. 2025Stick-Breaking Mixture Normalizing Flows with Component-Wise Tail Adaptation for Variational Inferencecited by 0