mlsanityData to 7 Oct 2026

Causally Disentangled Generative Variational AutoEncoder

arXiv 2302.11737 ↗First posted 23 Feb 2023stat.ML cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We present a new supervised learning technique for the Variational AutoEncoder (VAE) that allows it to learn a causally disentangled representation and generate causally disentangled outcomes simultaneously. We call this approach Causally Disentangled Generation (CDG). CDG is a generative model that accurately decodes an output based on a causally disentangled representation. Our research demonstrates that adding supervised regularization to the encoder alone is insufficient for achieving a generative model with CDG, even for a simple task. Therefore, we explore the necessary and sufficient conditions for achieving CDG within a specific model. Additionally, we introduce a universal metric for evaluating the causal disentanglement of a generative model. Empirical results from both image and tabular datasets support our findings.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 36 of its 52 references that are in the map. First posted on arXiv 23 Feb 2023.

Builds on

36 of 52 references.

References · 36

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  4. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  7. 2019Modeling Tabular data using Conditional GANcited by 695
  8. 2014Semi-Supervised Learning with Deep Generative Modelscited by 494
  9. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  10. 2019CLEVRER: CoLlision Events for Video REpresentation and Reasoningcited by 475
  11. 2015Importance Weighted Autoencoderscited by 454
  12. 2018Invertible Residual Networkscited by 364
24 more
  1. 2019DAG-GNN: DAG Structure Learning with Graph Neural Networkscited by 329
  2. 2019Learning Sparse Nonparametric DAGscited by 207
  3. 2019A Meta-Transfer Objective for Learning to Disentangle Causal Mechanismscited by 158
  4. 2021Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICAcited by 158
  5. 2021CTAB-GAN: Effective Table Data Synthesizingcited by 156
  6. 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
  7. 2018Robustly Disentangled Causal Mechanisms: Validating Deep Representations for Interventional Robustnesscited by 108
  8. 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
  9. 2020On Disentangled Representations Learned From Correlated Datacited by 94
  10. 2018Learning Disentangled Joint Continuous and Discrete Representationscited by 83
  11. 2022Identifiability of deep generative models without auxiliary informationcited by 70
  12. 2020Weakly Supervised Disentangled Generative Causal Representation Learningcited by 67
  13. 2019Disentangling Factors of Variation Using Few Labelscited by 57
  14. 2021CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoningcited by 23
  15. 2021On Causally Disentangled Representationscited by 22
  16. 2019Copulas as High-Dimensional Generative Models: Vine Copula Autoencoderscited by 20
  17. 2019Learning Representations by Maximizing Mutual Information in Variational Autoencoderscited by 20
  18. 2018Disentangling Latent Space for VAE by Label Relevant/Irrelevant Dimensionscited by 19
  19. 2021Causal-TGAN: Generating Tabular Data Using Causal Generative Adversarial Networkscited by 12
  20. 2017Challenges in Disentangling Independent Factors of Variationcited by 10
  21. 2020A Generalised Linear Model Framework for β-Variational Autoencoders based on Exponential Dispersion Familiescited by 7
  22. 2021Semi-Supervised Disentanglement of Class-Related and Class-Independent Factors in VAEcited by 7
  23. 2021EXoN: EXplainable encoder Networkcited by 4
  24. 2020Bayesian Structure Learning in Multi-layered Genomic Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025CAUSAL3D: A Comprehensive Benchmark for Causal Learning from Visual Datacited by 7
  2. 2026Causal Transfer in Medical Image Analysiscited by 0