Semi-Supervised Learning with Deep Generative Models

Code

• github.com/dpkingma/nips14-ssl
  OfficialIn papernone★ 0
• github.com/enalisnick/stick-breaking_dgms
  none★ 96
• github.com/anonyme20/nips20
  none★ 6
• github.com/taranO/IB-semi-supervised-classification
  none★ 6
• github.com/numfah23/VAE
  pytorch★ 0
• github.com/leequant761/Gumbel-SSVAE
  pytorch★ 0
• github.com/HongleiXie/demo-CVAE
  tf★ 0
• github.com/jonemeth/generative-models
  pytorch★ 0
• github.com/ruishu/vae-clustering
  tf★ 0
• github.com/bynchang/semi-supervised-VAE
  pytorch★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions