Year: 2022
Type: preprint
Abstract: Exemplar-based methods rely on informative data points or prototypes to guide the optimization of learning algorithms. Such data facilitate interpretable model design and prediction. Of particular interest is the utility of exemplars in learning unsupervised deep representations. In this paper, we leverage hubs, which emerge as frequent neighbors in high-dimensional spaces, as exemplars to regularize a variational autoencoder and to learn a discriminative embedding for unsupervised down-stream tasks. We propose an unsupervised, data-driven regularization of the latent space with a mixture of hub-based priors and a hub-based contrastive loss. Experimental evaluation shows that our algorithm achieves superior cluster separability in the embedding space, and accurate data reconstruction and generation, compared to baselines and state-of-the-art techniques.
Source: arXiv (Cornell University)
Authors: Mani, Priya, Domeniconi, Carlotta
Institution: George Mason University
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4309795406