Open access
Date
2024-07Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000648934Publication status
publishedExternal links
Book title
Advances in Neural Information Processing Systems 36Pages / Article No.
Publisher
CurranEvent
Organisational unit
09670 - Vogt, Julia / Vogt, Julia
Related publications and datasets
Is new version of: https://doi.org/10.48550/ARXIV.2306.08984
Notes
Poster presentation on December 12, 2023.More
Show all metadata
ETH Bibliography
yes
Altmetrics