Semi-supervised generation with cluster-aware generative models

Authors: Lars Maaløe, Marco Fraccaro, Ole Winther

Authors: Lars Maaløe, Marco Fraccaro, Ole Winther

Publication date: 2017/4/3

Journal: arXiv preprint arXiv:1704.00637

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.


Similar posts

Sign up for insights from raffle

Get the latest resources, events and webinars sent straight to your inbox. You'll learn about AI, customer service, employee engagement and much more with our knowledge-filled newsletter.