mlsanityData to 14 Oct 2026

DeCaFlow: A deconfounding causal generative model

arXiv 2503.15114 ↗First posted 19 Mar 2025cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate causal inference on continuous variables under the presence of hidden confounders. Specifically, we extend previous results on causal estimation under hidden confounding to show that a single instance of DeCaFlow provides correct estimates for all causal queries identifiable with do-calculus, leveraging proxy variables to adjust for the causal effects when do-calculus alone is insufficient. Moreover, we show that counterfactual queries are identifiable as long as their interventional counterparts are identifiable, and thus are also correctly estimated by DeCaFlow. Our empirical results on diverse settings (including the Ecoli70 dataset, with 3 independent hidden confounders, tens of observed variables and hundreds of causal queries) show that DeCaFlow outperforms existing approaches, while demonstrating its out-of-the-box applicability to any given causal graph. An implementation can be found in https://github.com/aalmodovares/DeCaFlow

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 42 of its 94 references that are in the map. First posted on arXiv 19 Mar 2025.

Builds on

42 of 94 references.

References · 42

  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
  2. 2017Counterfactual Fairnesscited by 804
  3. 2014Certifying and removing disparate impactcited by 715
  4. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  5. 2019Neural Spline Flowscited by 596
  6. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  7. 2018Pyro: Deep Universal Probabilistic Programmingcited by 380
  8. 2021Self-Supervised Learning with Data Augmentations Provably Isolates Content from Stylecited by 312
  9. 2015MADE: Masked Autoencoder for Distribution Estimationcited by 307
  10. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 211
  11. 2019Learning Likelihoods with Conditional Normalizing Flowscited by 172
  12. 2017CausalGAN: Learning Causal Implicit Generative Models with Adversarial Trainingcited by 152
30 more
  1. 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 139
  2. 2018The Blessings of Multiple Causescited by 104
  3. 2020Causal Autoregressive Flowscited by 99
  4. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 98
  5. 2020An Introduction to Proximal Causal Learningcited by 95
  6. 2022On the Identifiability of Nonlinear ICA: Sparsity and Beyondcited by 85
  7. 2019Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounderscited by 75
  8. 2024Causal machine learning for predicting treatment outcomescited by 74
  9. 2022Causal Machine Learning for Healthcare and Precision Medicinecited by 68
  10. 2020Semiparametric proximal causal inferencecited by 59
  11. 2022Neural Causal Models for Counterfactual Identification and Estimationcited by 57
  12. 2023Posterior Collapse and Latent Variable Non-identifiabilitycited by 57
  13. 2021Proximal Causal Learning with Kernels: Two-Stage Estimation and Moment Restrictioncited by 55
  14. 2018Interval Estimation of Individual-Level Causal Effects Under Unobserved Confoundingcited by 51
  15. 2023Causal normalizing flows: from theory to practicecited by 51
  16. 2020CausalVAE: Structured Causal Disentanglement in Variational Autoencodercited by 48
  17. 2023Provably Learning Object-Centric Representationscited by 45
  18. 2023Counterfactual Identifiability of Bijective Causal Modelscited by 43
  19. 2021Relating Graph Neural Networks to Structural Causal Modelscited by 41
  20. 2022DoWhy-GCM: An extension of DoWhy for causal inference in graphical causal modelscited by 41
  21. 2022Indeterminacy in Generative Models: Characterization and Strong Identifiabilitycited by 33
  22. 2018Causal Inference with Noisy and Missing Covariates via Matrix Factorizationcited by 30
  23. 2021A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Modelscited by 29
  24. 2018Identifying Causal Effects with the R Package causaleffectcited by 19
  25. 2020Identifying effects of multiple treatments in the presence of unmeasured confoundingcited by 16
  26. 2018Multiple Causal Inference with Latent Confoundingcited by 14
  27. 2022Deep Learning Methods for Proximal Inference via Maximum Moment Restrictioncited by 14
  28. 2023Structured Neural Networks for Density Estimation and Causal Inferencecited by 13
  29. 2024Modular Learning of Deep Causal Generative Models for High-dimensional Causal Inferencecited by 9
  30. 2024Marginal Causal Flows for Validation and Inferencecited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025DoFlow: Flow-based Generative Models for Interventional and Counterfactual Forecasting on Time Seriescited by 4
  2. 2025Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inferencecited by 3
  3. 2026CausalWrap: Model-Agnostic Causal Constraint Wrappers for Tabular Synthetic Datacited by 2
  4. 2025Partially Functional Dynamic Backdoor Diffusion-based Causal Modelcited by 0
  5. 2026Physical Simulators as Do-Operators: Causal Discovery under Latent Confounders for AI-for-Sciencecited by 0
  6. 2026Decision-Aware Proximal Bridge Learning for Optimal Treatment Selectioncited by 0
  7. 2026Learning Hierarchical Causal Representations of the Effects of Forcings on Temperature in Climate Modelscited by 0
  8. 2026Learning Causal Normalizing Flows from Incomplete Data via Observed-Data Likelihoodcited by 0