# Tree Variational Autoencoders

Source: [Tree Variational Autoencoders](<https://www.sota2.com/research/paper/68fa713f1e209131cea50142>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-24T20:20:58.662Z

Authors: Laura Manduchi, Moritz Vandenhirtz, Alain Ryser, Julia Vogt

Published: 2023-06-15T09:25:04.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Hierarchical Generative Modeling on Fashion-Mnist](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-fashion-mnist.md>): Hierarchical Generative Modeling; Fashion MNIST; DP: 53.4.

- [Lineage Inference on C. elegans 500–750](<https://www.sota2.com/research/sota/lineage-inference-on-c-elegans-500-750.md>): Lineage Inference; C. elegans 500–750; Ratio Observed Time Points: 62.8.

- [Hierarchical Generative Modeling on MNIST](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-mnist.md>): Hierarchical Generative Modeling; MNIST; DP: 87.9.

- [Hierarchical Generative Modeling on 20 Newsgroups text](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-20-newsgroups-text.md>): Hierarchical Generative Modeling; 20 Newsgroups text; DP: 17.5.

- [Hierarchical Generative Modeling on Cifar10 32x32 (50k samples)](<https://www.sota2.com/research/sota/hierarchical-generative-modeling-on-cifar10-32x32-50k-samples.md>): Hierarchical Generative Modeling; Cifar10 32x32 (50k samples); DP: 35.3.

- [Lineage Inference on LineageVAE Day 4](<https://www.sota2.com/research/sota/lineage-inference-on-lineagevae-day-4.md>): Lineage Inference; LineageVAE Day 4; Ratio of Observed Time Points: 30.4.

- [Lineage Inference on C. elegans 100–300](<https://www.sota2.com/research/sota/lineage-inference-on-c-elegans-100-300.md>): Lineage Inference; C. elegans 100–300; Ratio of Observed Time Points: 13.8.

- [Lineage Inference on LineageVAE Day 2](<https://www.sota2.com/research/sota/lineage-inference-on-lineagevae-day-2.md>): Lineage Inference; LineageVAE Day 2; Ratio of Observed Time Points: 12.1.

- [Lineage Inference on LineageVAE Day 6](<https://www.sota2.com/research/sota/lineage-inference-on-lineagevae-day-6.md>): Lineage Inference; LineageVAE Day 6; Ratio of Observed Time Points: 56.4.

- [Lineage Inference on C. elegans 300–500](<https://www.sota2.com/research/sota/lineage-inference-on-c-elegans-300-500.md>): Lineage Inference; C. elegans 300–500; Ratio of Observed Time Points: 32.5.

- [Cellular Lineage Inference on Weinreb (cell lineage)](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-weinreb-cell-lineage.md>): Cellular Lineage Inference; Weinreb (cell lineage); DP: 60.4.

- [Cellular Lineage Inference on ECL cell lineage 838k points celltype:10](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-ecl-cell-lineage-838k-points-celltype-10.md>): Cellular Lineage Inference; ECL cell lineage 838k points celltype:10; DP: 41.86.

- [Cellular Lineage Inference on Limb (cell lineage)](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-limb-cell-lineage.md>): Cellular Lineage Inference; Limb (cell lineage); DP: 34.7.

- [Cellular Lineage Inference on LHCO cell lineage](<https://www.sota2.com/research/sota/cellular-lineage-inference-on-lhco-cell-lineage.md>): Cellular Lineage Inference; LHCO cell lineage; DP: 38.3.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2306.08984>)

[PDF](<https://arxiv.org/pdf/2306.08984.pdf>)
