mlsanityData to 14 Oct 2026

Joint-stochastic-approximation Random Fields with Application to Semi-supervised Learning

arXiv 2505.20330 ↗First posted 24 May 2025cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Our examination of deep generative models (DGMs) developed for semi-supervised learning (SSL), mainly GANs and VAEs, reveals two problems. First, mode missing and mode covering phenomenons are observed in genertion with GANs and VAEs. Second, there exists an awkward conflict between good classification and good generation in SSL by employing directed generative models. To address these problems, we formally present joint-stochastic-approximation random fields (JRFs) -- a new family of algorithms for building deep undirected generative models, with application to SSL. It is found through synthetic experiments that JRFs work well in balancing mode covering and mode missing, and match the empirical data distribution well. Empirically, JRFs achieve good classification results comparable to the state-of-art methods on widely adopted datasets -- MNIST, SVHN, and CIFAR-10 in SSL, and simultaneously perform good generation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 24 of its 49 references that are in the map. First posted on arXiv 24 May 2025.

Builds on

24 of 49 references.

References · 24

  1. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  2. 2016Improved Techniques for Training GANscited by 2,970
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  4. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  5. 2016Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networkscited by 543
  6. 2015Adversarial Autoencoderscited by 364
  7. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 343
  8. 2016Ladder Variational Autoencoderscited by 318
  9. 2015Generative Moment Matching Networkscited by 257
  10. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  11. 2016Adversarially Learned Inferencecited by 216
  12. 2016Energy-based Generative Adversarial Networkcited by 119
12 more
  1. 2017Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networkscited by 107
  2. 2015Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networkscited by 95
  3. 2017Good Semi-supervised Learning that Requires a Bad GANcited by 86
  4. 2016Auxiliary Deep Generative Modelscited by 72
  5. 2016Cooperative Training of Descriptor and Generator Networkscited by 60
  6. 2017Triple Generative Adversarial Netscited by 60
  7. 2016Deep Directed Generative Models with Energy-Based Probability Estimationcited by 34
  8. 2017Calibrating Energy-based Generative Adversarial Networkscited by 13
  9. 2017Triangle Generative Adversarial Networkscited by 12
  10. 2014Generative Modeling of Convolutional Neural Networkscited by 5
  11. 2016Joint Stochastic Approximation learning of Helmholtz Machinescited by 5
  12. 2017Language modeling with Neural trans-dimensional random fieldscited by 4

Built on by

Not cited yet.