Semi-Supervised Generation with Cluster-aware Generative Models

Lars Maaløe, Marco Fraccaro, Ole Winther

Research output: Contribution to journalJournal articleResearchpeer-review

559 Downloads (Pure)

Abstract

Deep generative models trained with large amounts of unlabelled data have proven to be powerful within the domain of unsupervised learning. Many real life data sets contain a small amount of labelled data points, that are typically disregarded when training generative models. We propose the Cluster-aware Generative Model, that uses unlabelled information to infer a latent representation that models the natural clustering of the data, and additional labelled data points to refine this clustering. The generative performances of the model significantly improve when labelled information is exploited, obtaining a log-likelihood of −79.38 nats on permutation invariant MNIST, while also achieving competitive semi-supervised classification accuracies. The model can also be trained fully unsupervised, and still improve the log-likelihood
performance with respect to related methods.
Original languageEnglish
JournalarXiv
Number of pages10
Publication statusPublished - 2017

Fingerprint Dive into the research topics of 'Semi-Supervised Generation with Cluster-aware Generative Models'. Together they form a unique fingerprint.

Cite this