# Nonparametric Variational Auto-encoders for Hierarchical Representation Learning

arXiv: https://arxiv.org/abs/1703.07027 · HTML: https://mlsanity.com/paper/1703.07027/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2017.

## Built on by (most cited first, 22 of 22)

- [Multi-Facet Clustering Variational Autoencoders](https://mlsanity.com/paper/2106.05241/) (2021)
- [Clustering by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/2107.11635/) (2021)
- [Deep Bayesian Unsupervised Lifelong Learning](https://mlsanity.com/paper/2106.07035/) (2021)
- [t3-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence](https://mlsanity.com/paper/2312.01133/) (2023)
- [Tree Variational Autoencoders](https://mlsanity.com/paper/2306.08984/) (2023)
- [Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decoding](https://mlsanity.com/paper/2402.19009/) (2024)
- [Distantly Supervised Relation Extraction with Sentence Reconstruction and Knowledge Base Priors](https://mlsanity.com/paper/2104.08225/) (2021)
- [Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery](https://mlsanity.com/paper/2509.23602/) (2025)
- [Kanerva++: extending The Kanerva Machine with differentiable, locally block allocated latent memory](https://mlsanity.com/paper/2103.03905/) (2021)
- [From Logits to Hierarchies: Hierarchical Clustering made Simple](https://mlsanity.com/paper/2410.07858/) (2024)
- [TreeDiffusion: Hierarchical Generative Clustering for Conditional Diffusion](https://mlsanity.com/paper/2410.16910/) (2024)
- [Training Heterogeneous Features in Sequence to Sequence Tasks: Latent Enhanced Multi-filter Seq2Seq Model](https://mlsanity.com/paper/2105.08840/) (2021)
- [ByPE-VAE: Bayesian Pseudocoresets Exemplar VAE](https://mlsanity.com/paper/2107.09286/) (2021)
- [scTree: Discovering Cellular Hierarchies in the Presence of Batch Effects in scRNA-seq Data](https://mlsanity.com/paper/2406.19300/) (2024)
- [DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder](https://mlsanity.com/paper/2305.14067/) (2023)
- [A Metalearned Neural Circuit for Nonparametric Bayesian Inference](https://mlsanity.com/paper/2311.14601/) (2023)
- [Robotic Long-Horizon Manipulation with Bayesian Non-parametric Skill Priors](https://mlsanity.com/paper/2503.21975/) (2025)
- [Deep Contrastive Patch-Based Subspace Learning for Camera Image Signal Processing](https://mlsanity.com/paper/2104.00253/) (2021)
- [Multi-party Response Generation with Relation Disentanglement](https://mlsanity.com/paper/2403.10827/) (2024)
- [TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting](https://mlsanity.com/paper/2605.09208/) (2026)
- [A Unified Non-Parametric and Interpretable Point Cloud Analysis via t-FCW Graph Representation](https://mlsanity.com/paper/2605.15475/) (2026)
- [Knowledge Reutilization in Meta-Reinforcement Learning](https://mlsanity.com/paper/2606.18132/) (2026)

## Abstract (arXiv)

The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple prior over the latent variables such as standard normal distribution, thereby restricting its applications to relatively simple phenomena. In this work, we propose hierarchical nonparametric variational autoencoders, which combines tree-structured Bayesian nonparametric priors with VAEs, to enable infinite flexibility of the latent representation space. Both the neural parameters and Bayesian priors are learned jointly using tailored variational inference. The resulting model induces a hierarchical structure of latent semantic concepts underlying the data corpus, and infers accurate representations of data instances. We apply our model in video representation learning. Our method is able to discover highly interpretable activity hierarchies, and obtain improved clustering accuracy and generalization capacity based on the learned rich representations.