mlsanityData to 14 Oct 2026

Tree Variational Autoencoders

arXiv 2306.08984 ↗First posted 15 Jun 2023cs.LG cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We propose Tree Variational Autoencoder (TreeVAE), a new generative hierarchical clustering model that learns a flexible tree-based posterior distribution over latent variables. TreeVAE hierarchically divides samples according to their intrinsic characteristics, shedding light on hidden structures in the data. It adapts its architecture to discover the optimal tree for encoding dependencies between latent variables. The proposed tree-based generative architecture enables lightweight conditional inference and improves generative performance by utilizing specialized leaf decoders. We show that TreeVAE uncovers underlying clusters in the data and finds meaningful hierarchical relations between the different groups on a variety of datasets, including real-world imaging data. We present empirically that TreeVAE provides a more competitive log-likelihood lower bound than the sequential counterparts. Finally, due to its generative nature, TreeVAE is able to generate new samples from the discovered clusters via conditional sampling.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 37 of its 82 references that are in the map. First posted on arXiv 15 Jun 2023.

Builds on

37 of 82 references.

References · 37

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  6. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,845
  7. 2019An Introduction to Variational Autoencoderscited by 1,000
  8. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  10. 2016Ladder Variational Autoencoderscited by 318
  11. 2020Contrastive Clusteringcited by 265
  12. 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
25 more
  1. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  2. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  3. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 191
  4. 2019Continuous Hierarchical Representations with Poincar'e Variational Auto-Encoderscited by 112
  5. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  6. 2015Hierarchical Variational Modelscited by 89
  7. 2018Adaptive Neural Treescited by 64
  8. 2022Twin Contrastive Learning for Online Clusteringcited by 60
  9. 2019Learning Hierarchical Priors in VAEscited by 53
  10. 2015Scalable Sparse Subspace Clustering by Orthogonal Matching Pursuitcited by 50
  11. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  12. 2023Explicitly Minimizing the Blur Error of Variational Autoencoderscited by 31
  13. 2017Faithful Inversion of Generative Models for Effective Amortized Inferencecited by 29
  14. 2018Leveraging the Exact Likelihood of Deep Latent Variable Modelscited by 23
  15. 2017Nonparametric Variational Auto-encoders for Hierarchical Representation Learningcited by 22
  16. 2022Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curvecited by 18
  17. 2021Connecting Interpretability and Robustness in Decision Trees through Separationcited by 16
  18. 2021Deep Conditional Gaussian Mixture Model for Constrained Clusteringcited by 14
  19. 2022POETREE: Interpretable Policy Learning with Adaptive Decision Treescited by 14
  20. 2021Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Surveycited by 10
  21. 2023A Multi-Resolution Framework for U-Nets with Applications to Hierarchical VAEscited by 9
  22. 2022Unsupervised Object Representation Learning using Translation and Rotation Group Equivariant VAEcited by 8
  23. 2019Hierarchically Clustered Representation Learningcited by 6
  24. 2023Trading Information between Latents in Hierarchical Variational Autoencoderscited by 6
  25. 2018The LORACs prior for VAEs: Letting the Trees Speak for the Datacited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 2; 2026: 3.

10 papers.

  1. 2024From Logits to Hierarchies: Hierarchical Clustering made Simplecited by 3
  2. 2024TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusioncited by 3
  3. 2024Weakly Augmented Variational Autoencoder in Time Series Anomaly Detectioncited by 2
  4. 2024scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Datacited by 2
  5. 2026Foundation Model for Cardiac Time Series via Masked Latent Attentioncited by 1
  6. 2024Structured Generations: Using Hierarchical Clusters to guide Diffusion Modelscited by 0
  7. 2025HDTree: Generative Modeling of Cellular Hierarchies for Robust Lineage Inferencecited by 0
  8. 2025Disentangled representations via score-based variational autoencoderscited by 0
  9. 2026Classification Fields: Arbitrarily Fine Recursive Hierarchical Clustering From Few Examplescited by 0
  10. 2026Diffusion Models and Concept Formationcited by 0