mlsanityData to 7 Oct 2026

Deep Dive into Semi-Supervised ELBO for Improving Classification Performance

arXiv 2108.12734 ↗First posted 29 Aug 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Decomposition of the evidence lower bound (ELBO) objective of VAE used for density estimation revealed the deficiency of VAE for representation learning and suggested ways to improve the model. In this paper, we investigate whether we can get similar insights by decomposing the ELBO for semi-supervised classification using VAE model. Specifically, we show that mutual information between input and class labels decreases during maximization of ELBO objective. We propose a method to address this issue. We also enforce cluster assumption to aid in classification. Experiments on a diverse datasets verify that our method can be used to improve the classification performance of existing VAE based semi-supervised models. Experiments also show that, this can be achieved without sacrificing the generative power of the model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 41 references that are in the map. First posted on arXiv 29 Aug 2021.

Builds on

26 of 41 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  5. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,265
  6. 2018Deep Graph Infomaxcited by 1,101
  7. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  8. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  9. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  10. 2018Deep Learning for Classical Japanese Literaturecited by 415
  11. 2016Ladder Variational Autoencoderscited by 315
  12. 2017VAE with a VampPriorcited by 247
14 more
  1. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  2. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  3. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 94
  4. 2019A Mutual Information Maximization Perspective of Language Representation Learningcited by 85
  5. 2016Auxiliary Deep Generative Modelscited by 72
  6. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  7. 2018Structured Disentangled Representationscited by 62
  8. 2018Distribution Matching in Variational Inferencecited by 35
  9. 2019Learning Representations by Maximizing Mutual Information in Variational Autoencoderscited by 20
  10. 2016Semi-Supervised Learning with Context-Conditional Generative Adversarial Networkscited by 19
  11. 2017Disentangled Variational Auto-Encoder for Semi-supervised Learningcited by 17
  12. 2018Graph Partition Neural Networks for Semi-Supervised Classificationcited by 17
  13. 2020VMI-VAE: Variational Mutual Information Maximization Framework for VAE With Discrete and Continuous Priorscited by 4
  14. 2020MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximizationcited by 4

Built on by

Not cited yet.