Improving Semi-Supervised Learning with Auxiliary Deep Generative Models

By Lars Maaløe, Casper Kaae Sønderby, Søren Kaae Sønderby, Ole Winther. 2015

28 citations recorded by the source corpus.

Subfields: Generative Models

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Generative Models

1. Stefano Ermon
2. Pieter Abbeel
3. Jiaming Song
4. Lars Maaløe
5. Ole Winther
6. Aaron C. Courville
7. Arash Vahdat
8. Max Welling

Citations in the corpus

• InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets (2016, methodology): “Another intriguing line of work consists of the ladder network [14], which has achieved spectacular results on a semi-supervised variant of the MNIST dataset.”
• How to Train Deep Variational Autoencoders and Probabilistic Ladder Networks (2016, background): “DGMs have later been shown to be a powerful framework for semi-supervised learning (Kingma et al., 2014; Maaloee et al., 2016).”
• Deep generative models for reject inference in credit scoring (2019, methodology): “and ˚jointly and estimates , ˙2, and ˇthat maximize the approximated log likelihood at each iteration. 3.3 Model 2: Generative and inference processes Model 2 uses auxiliary variables introduced in [33, 34] in the context of deep generative models. Models with auxiliary variables improve the variati”