Pith. sign in

REVIEW 1 cited by

The Variational Homoencoder: Learning to learn high capacity generative models from few examples

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.08919 v1 pith:TSOYFVKS submitted 2018-07-24 cs.LG cs.AIstat.ML

The Variational Homoencoder: Learning to learn high capacity generative models from few examples

classification cs.LG cs.AIstat.ML
keywords hierarchicalmodelgenerativelatentvariationalclassificationdatasetdevelop
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Hierarchical Bayesian methods can unify many related tasks (e.g. k-shot classification, conditional and unconditional generation) as inference within a single generative model. However, when this generative model is expressed as a powerful neural network such as a PixelCNN, we show that existing learning techniques typically fail to effectively use latent variables. To address this, we develop a modification of the Variational Autoencoder in which encoded observations are decoded to new elements from the same class. This technique, which we call a Variational Homoencoder (VHE), produces a hierarchical latent variable model which better utilises latent variables. We use the VHE framework to learn a hierarchical PixelCNN on the Omniglot dataset, which outperforms all existing models on test set likelihood and achieves strong performance on one-shot generation and classification tasks. We additionally validate the VHE on natural images from the YouTube Faces database. Finally, we develop extensions of the model that apply to richer dataset structures such as factorial and hierarchical categories.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations

    cs.LG 2026-06 unverdicted novelty 7.0

    CoMetaPNS combines meta-learned neural surrogates with a continual Bayesian Gaussian Mixture Model to adapt cardiac electrophysiology simulations to new data while avoiding catastrophic forgetting.