mlsanityData to 14 Oct 2026

EXoN: EXplainable encoder Network

arXiv 2105.10867 ↗First posted 23 May 2021stat.ML cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We propose a new semi-supervised learning method of Variational AutoEncoder (VAE) which yields a customized and explainable latent space by EXplainable encoder Network (EXoN). Customization means a manual design of latent space layout for specific labeled data. To improve the performance of our VAE in a classification task without the loss of performance as a generative model, we employ a new semi-supervised classification method called SCI (Soft-label Consistency Interpolation). The classification loss and the Kullback-Leibler divergence play a crucial role in constructing explainable latent space. The variability of generated samples from our proposed model depends on a specific subspace, called activated latent subspace. Our numerical results with MNIST and CIFAR-10 datasets show that EXoN produces an explainable latent space and reduces the cost of investigating representation patterns on the latent space.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 23 May 2021.

Builds on

32 of 48 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2017Neural Discrete Representation Learningcited by 4,712
  5. 2016Improved Techniques for Training GANscited by 2,970
  6. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
  8. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  9. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  10. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  11. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  12. 2014Semi-Supervised Learning with Deep Generative Modelscited by 496
20 more
  1. 2020In-Domain GAN Inversion for Real Image Editingcited by 420
  2. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 363
  3. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  4. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 251
  5. 2016Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoderscited by 220
  6. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 121
  7. 2019Preventing Posterior Collapse with delta-VAEscited by 86
  8. 2017Improved Variational Autoencoders for Text Modeling using Dilated Convolutionscited by 81
  9. 2016Auxiliary Deep Generative Modelscited by 72
  10. 2017Learning Disentangled Representations with Semi-Supervised Deep Generative Modelscited by 72
  11. 2019Topic-Guided Variational Autoencoders for Text Generationcited by 44
  12. 2019Self-supervised GAN: Analysis and Improvement with Multi-class Minimax Gamecited by 25
  13. 2018Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionscited by 19
  14. 2020Improving GAN Training with Probability Ratio Clipping and Sample Reweightingcited by 18
  15. 2017Disentangled Variational Auto-Encoder for Semi-supervised Learningcited by 17
  16. 2019Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoderscited by 13
  17. 2019Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoderscited by 9
  18. 2020SHOT-VAE: Semi-supervised Deep Generative Models With Label-aware ELBO Approximationscited by 8
  19. 2021Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAEcited by 7
  20. 2017Semi-Supervised Generation with Cluster-aware Generative Modelscited by 6

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2023Prototypical Self-Explainable Models Without Re-trainingcited by 6
  2. 2022Explaining Image Classifiers Using Contrastive Counterfactuals in Generative Latent Spacescited by 4
  3. 2023Causally Disentangled Generative Variational AutoEncodercited by 2
  4. 2024Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantizationcited by 0