Semi-Supervised Learning with Deep Generative Models
Diederik P. Kingma, Danilo Jimenez Rezende, Shakir Mohamed et al. · UvA-DARE (University of Amsterdam) · 2014
The ever-increasing size of modern data sets combined with the difficulty of obtaining label information has made semi-supervised learning one of the problems of significant practical importance in modern data analysis. We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones. Generative approaches have thus far been either inflexible, inefficient or non-scalable. We show that deep generative models and approximate Bayesian inference exploiting recent advances in variational methods can be used to provide significant improvements, making generative approaches highly competitive for semi-supervised learning.
Cited by 1,415 works. doi:10.48550/arxiv.1406.5298 Open-access PDF
Authors
References
- Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
- Auto-Encoding Variational Bayes
- Solving Multiclass Learning Problems via Error-Correcting Output Codes
- Reading digits in natural images with unsupervised feature learning
- Transductive Inference for Text Classification using Support Vector Machines
- Semi-supervised learning using Gaussian fields and harmonic functions
- Semi-Supervised Learning Literature Survey
- Semi-supervised learning of compact document representations with deep networks
- Semi-Supervised Self-Training of Object Detection Models
- Semi-Supervised Learning for Natural Language