Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Tree Variational Autoencoders

About

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.

Laura Manduchi, Moritz Vandenhirtz, Alain Ryser, Julia Vogt• 2023

Related benchmarks

TaskDatasetResultRank
Cellular Lineage InferenceLimb (cell lineage)
DP34.7
14
Cellular Lineage InferenceWeinreb (cell lineage)
DP60.4
12
Cellular Lineage InferenceLHCO cell lineage
DP38.3
12
Hierarchical Generative ModelingFashion MNIST
DP53.4
7
Hierarchical Generative ModelingMNIST
DP87.9
7
Hierarchical Generative Modeling20 Newsgroups text
DP17.5
7
Hierarchical Generative ModelingCifar10 32x32 (50k samples)
DP35.3
6
Lineage InferenceLineageVAE Day 4
Ratio of Observed Time Points30.4
5
Lineage InferenceLineageVAE Day 2
Ratio of Observed Time Points12.1
5
Lineage InferenceLineageVAE Day 6
Ratio of Observed Time Points56.4
5
Showing 10 of 14 rows

Other info

Follow for update