Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

Zekun Wang, Ethan Haarer, Tianyi Zhu, Zhiyi Dai, Christopher J. MacLellan

Keywords: unsupervised learning, hierarchical clustering, representation learning, latent variable models, prototype discovery

TL;DR: We introduce Deep Taxonomic Networks, a deep latent variable approach that uses a complete binary-tree mixture-of-Gaussians prior in a VAE framework to discover interpretable hierarchical taxonomies and prototype clusters from unlabeled data

Abstract:

Inspired by the human ability to learn and organize knowledge into hierarchical taxonomies with prototypes, this paper addresses key limitations in current deep hierarchical clustering methods.
Existing methods often tie the structure to the number of classes and underutilize the rich prototype information available at intermediate hierarchical levels.
We introduce deep taxonomic networks, a novel deep latent variable approach designed to bridge these gaps.
Our method optimizes a large latent taxonomic hierarchy, specifically a complete binary tree structured mixture-of-Gaussian prior within a variational inference framework, to automatically discover taxonomic structures and associated prototype clusters directly from unlabeled data without assuming true label sizes.
We analytically show that optimizing the ELBO of our method encourages the discovery of hierarchical relationships among prototypes.
Empirically, our learned models demonstrate strong hierarchical clustering performance, outperforming baselines across diverse image classification datasets using our novel evaluation mechanism that leverages prototype clusters discovered at all hierarchical levels.
Qualitative results further reveal that deep taxonomic networks discover rich and interpretable hierarchical taxonomies, capturing both coarse-grained semantic categories and fine-grained visual distinctions.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 23833