Hub-VAE: Unsupervised Hub-based Regularization of Variational Autoencoders
This work addresses the challenge of improving unsupervised representation learning for downstream tasks like clustering, though it appears incremental as it builds on existing hub-based and VAE methods.
The paper tackled the problem of learning discriminative embeddings for unsupervised tasks by using hubs as exemplars to regularize variational autoencoders, achieving superior cluster separability and accurate reconstruction/generation compared to baselines.
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.