# Semi-Supervised Generation with Cluster-aware Generative Models

arXiv: https://arxiv.org/abs/1704.00637 · HTML: https://mlsanity.com/paper/1704.00637/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Apr 2017.

## Built on by (most cited first, 6 of 6)

- [Hierarchical VAEs Know What They Don't Know](https://mlsanity.com/paper/2102.08248/) (2021)
- [Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders](https://mlsanity.com/paper/2306.05023/) (2023)
- [EXoN: EXplainable encoder Network](https://mlsanity.com/paper/2105.10867/) (2021)
- [Discouraging posterior collapse in hierarchical Variational Autoencoders using context](https://mlsanity.com/paper/2302.09976/) (2023)
- [Anomaly Detection in Aeronautics Data with Quantum-compatible Discrete Deep Generative Model](https://mlsanity.com/paper/2303.12302/) (2023)
- [Guided Generative Models using Weak Supervision for Detecting Object Spatial Arrangement in Overhead Images](https://mlsanity.com/paper/2112.05786/) (2021)

## Abstract (arXiv)

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.