mlsanityData to 14 Oct 2026

Discovery of Single Independent Latent Variable

arXiv 2110.05887 ↗First posted 12 Oct 2021stat.ML cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Latent variable discovery is a central problem in data analysis with a broad range of applications in applied science. In this work, we consider data given as an invertible mixture of two statistically independent components and assume that one of the components is observed while the other is hidden. Our goal is to recover the hidden component. For this purpose, we propose an autoencoder equipped with a discriminator. Unlike the standard nonlinear ICA problem, which was shown to be non-identifiable, in the special case of ICA we consider here, we show that our approach can recover the component of interest up to entropy-preserving transformation. We demonstrate the performance of the proposed approach in several tasks, including image synthesis, voice cloning, and fetal ECG extraction.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 24 of its 67 references that are in the map. First posted on arXiv 12 Oct 2021.

Builds on

24 of 67 references.

References · 24

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2015Domain-Adversarial Training of Neural Networkscited by 3,044
  4. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  5. 2016InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Netscited by 860
  6. 2018Disentangling by Factorisingcited by 616
  7. 2017The Perception-Distortion Tradeoffcited by 587
  8. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  9. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 354
  10. 2018Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learningcited by 282
  11. 2016Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICAcited by 273
  12. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 241
12 more
  1. 2018Isolating Sources of Disentanglement in Variational Autoencoderscited by 167
  2. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  3. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 92
  4. 2019The Incomplete Rosetta Stone Problem: Identifiability Results for Multi-View Nonlinear ICAcited by 86
  5. 2019Jasper: An End-to-End Convolutional Neural Acoustic Modelcited by 76
  6. 2018Structured Disentangled Representationscited by 62
  7. 2017Learning Independent Features with Adversarial Nets for Non-linear ICAcited by 33
  8. 2015Nonparametric Canonical Correlation Analysiscited by 22
  9. 2018A Universal Music Translation Networkcited by 22
  10. 2020ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integrationcited by 22
  11. 2019Unsupervised Singing Voice Conversioncited by 14
  12. 2019TTS Skins: Speaker Conversion via ASRcited by 14

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Seriescited by 59
  2. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 43
  3. 2025Provable Speech Attributes Conversion via Latent Independencecited by 1