Tree Variational Autoencoders
This work addresses hierarchical clustering and generative modeling for data analysis, representing an incremental advancement by combining tree structures with variational autoencoders.
The paper tackles the problem of learning hierarchical clustering and generative modeling by proposing TreeVAE, which learns a tree-based posterior distribution to uncover hidden structures and improve generative performance, achieving a more competitive log-likelihood lower bound than sequential counterparts.
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.