Lune

NeurIPS2022Top-tier venue

Discovery of Single Independent Latent Variable

Uri Shaham, Jonathan Svirsky, Ori Katz, Ronen Talmon

Abstract

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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-SeriesYihe Wang, Yu Han, Haishuai Wang, Xiang ZhangNeurIPS 2023 · 106 citations
  2. Counterfactual Identifiability of Bijective Causal ModelsArash Nasr-Esfahany, Mohammad Alizadeh, Devavrat ShahICML 2023 · 42 citations

Builds on1

  1. Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)Peter Sorrenson, Carsten Rother, Ullrich KötheICLR 2020 · 132 citations

Related papers

  1. Learning Disentangled Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE ApproachMinyoung Kim, Ricardo Guerrero, Vladimir PavlovicACM MM 2021 · 4 citations
  2. On the Identifiability of Nonlinear ICA: Sparsity and BeyondYujia Zheng, Ignavier Ng, Kun ZhangNeurIPS 2022 · 104 citations
  3. On the identifiability of causal graphs with multiple environmentsFrancesco MontagnaICLR 2026 · 2 citations
  4. On Linear Identifiability of Learned RepresentationsGeoffrey Roeder, Luke Metz, Durk KingmaICML 2021 · 107 citations
  5. CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal ConversionAnders Vestergaard Nørskov, Alexander Neergaard Zahid, Morten MørupNeurIPS 2023 · 14 citations
Dusk over the sea between two cliffs drawn in fine vertical lines