mlsanityData to 14 Oct 2026

A Revisit of Total Correlation in Disentangled Variational Auto-Encoder with Partial Disentanglement

arXiv 2502.02279 ↗First posted 4 Feb 2025cs.LG q-bio.NCcited by 3

Not on the map. Why?

Abstract (arXiv)

A fully disentangled variational auto-encoder (VAE) aims to identify disentangled latent components from observations. However, enforcing full independence between all latent components may be too strict for certain datasets. In some cases, multiple factors may be entangled together in a non-separable manner, or a single independent semantic meaning could be represented by multiple latent components within a higher-dimensional manifold. To address such scenarios with greater flexibility, we develop the Partially Disentangled VAE (PDisVAE), which generalizes the total correlation (TC) term in fully disentangled VAEs to a partial correlation (PC) term. This framework can handle group-wise independence and can naturally reduce to either the standard VAE or the fully disentangled VAE. Validation through three synthetic experiments demonstrates the correctness and practicality of PDisVAE. When applied to real-world datasets, PDisVAE discovers valuable information that is difficult to find using fully disentangled VAEs, implying its versatility and effectiveness.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 4 Feb 2025.

Builds on

14 of 35 references.

References · 14

  1. 2014Deep Learning Face Attributes in the Wildcited by 3,693
  2. 2016Variational Inference: A Review for Statisticianscited by 1,472
  3. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  4. 2016Deep Variational Information Bottleneckcited by 930
  5. 2018Disentangling by Factorisingcited by 616
  6. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 503
  7. 2015Adversarial Autoencoderscited by 364
  8. 2020Disentanglement by Nonlinear ICA with General Incompressible-flow Networks (GIN)cited by 92
  9. 2022Weakly Supervised Representation Learning with Sparse Perturbationscited by 65
  10. 2020Learning identifiable and interpretable latent models of high-dimensional neural activity using pi-VAEcited by 48
  11. 2023Disentanglement via Latent Quantizationcited by 40
  12. 2024Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Modelscited by 9
2 more
  1. 2019Independent Subspace Analysis for Unsupervised Learning of Disentangled Representationscited by 8
  2. 2024α-TCVAE: On the relationship between Disentanglement and Diversitycited by 4

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025BrainStratify: Coarse-to-Fine Disentanglement of Intracranial Neural Dynamicscited by 1
  2. 2025A Factorized Low-Rank RNN Framework for Uncovering Independent Neural Latent Dynamics and Connectivitycited by 1
  3. 2025Uncovering Semantic Selectivity of Latent Groups in Higher Visual Cortex with Mutual Information-Guided Diffusioncited by 0