10.25673/122856">


Proceedings of International Conference on Applied Innovation in IT
2025/12/22, Volume 13, Issue 5, pp.219-231

Interventional Deep Generative Models for Scalable Causal Discovery and Counterfactual Analysis


Saif Hameed Abbood, Ahmed Fadhil Qutaif, Zainab Mohanad Issa and Haza Nuzly Abdull Hamed


Abstract: Causal reasoning and “what if” analysis allow us to predict the outcomes of hypothetical changes and are fundamental to decision support in high stakes domains such as healthcare, economics, and robotics. Traditional causal discovery methods can find cause and effect graphs under simple assumptions but struggle with large, complex datasets and cannot predict what might happen after a hypothetical change. Algorithms like PC, FCI, and NOTEARS reliably infer directed acyclic graphs (DAGs) under linear or simple nonlinear assumptions but fail to scale to high dimensional data and lack mechanisms for counterfactual simulation. Conversely, deep generative models learn to reproduce complex data patterns but do not capture cause and effect relationships, so they cannot answer “what if” questions. We propose Interventional Structural Deep Generative Models (IS DGM), a unified framework that embeds a learnable DAG into the latent space of a variational autoencoder. We prove that, under realistic conditions, our approach can uniquely recover the true causal structure and generate reliable counterfactual predictions. IS DGM enforces acyclicity via a continuous matrix exponential penalty, encourages sparsity through regularization, and introduces a latent space intervention operator to clamp selected factors and propagate effects through the graph. Under mild exponential family priors and with diverse interventional data, IS DGM recovers the true DAG up to element wise reparameterization. Empirically, on synthetic benchmarks (latent dimensions up to 100), IS DGM reduces structural Hamming distance by 30–55% and achieves over 50% lower counterfactual RMSE than state of the art baselines. On real clinical data (MIMIC III), it halves prediction error of treatment response simulations relative to identifiable VAEs and NOTEARS. Ablation studies confirm the necessity of each loss component, and scalability analyses quantify runtime and memory trade offs. IS DGM thus offers a principled, scalable solution for joint causal discovery and counterfactual inference in complex, high dimensional settings.

Keywords: Artificial intelligence, Causal Discovery, Deep Generative Models, Latent Space Interventions, Directed Acyclic Graph (DAG) Learning, Identifiability, Counterfactual Inference, Structural Hamming Distance (SHD).

DOI: 10.25673/122856

Download: PDF

References:

  1. J. Pearl, Causality: Models, Reasoning and Inference, 2nd ed., USA: Cambridge University Press, 2009.
  2. P. Spirtes, C. Glymour, and R. Scheines, Causation, Prediction, and Search, vol. 81, 1993, , doi: 10.1007/978-1-4612-2748-9.
  3. J. Peters, D. Janzing, and B. Schlkopf, Elements of Causal Inference: Foundations and Learning Algorithms, The MIT Press, 2017.
  4. M. H. Maathuis, D. Colombo, M. Kalisch, and P. Bühlmann, “Predicting causal effects in large-scale systems from observational data,” Nature Methods, vol. 7, no. 4, pp. 247-248, 2010, , doi: 10.1038/nmeth0410-247.
  5. D. P. Kingma and M. Welling, “Auto-Encoding Variational Bayes,” 2022.
  6. D. J. Rezende and S. Mohamed, “Variational Inference with Normalizing Flows,” 2016.
  7. Y. Choi, M. Choi, M. Kim, J.-W. Ha, S. Kim, and J. Choo, “Stargan: Unified generative adversarial networks for multi-domain image-to-image translation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8789-8797.
  8. K. Sachs, O. Perez, D. Pe’er, D. A. Lauffenburger, and G. P. Nolan, “Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data,” Science, vol. 308, no. 5721, pp. 523-529, Apr. 2005, , doi: 10.1126/science.1105809.
  9. X. Zheng, B. Aragam, P. Ravikumar, and E. P. Xing, “DAGs with NO TEARS: Continuous Optimization for Structure Learning,” 2018.
  10. I. Khemakhem, D. P. Kingma, R. P. Monti, and A. Hyvärinen, “Variational Autoencoders and Nonlinear ICA: A Unifying Framework,” 2020.
  11. A. Hyvärinen and P. Pajunen, “Nonlinear independent component analysis: Existence and uniqueness results,” Neural Networks, vol. 12, no. 3, pp. 429-439, 1999, , [Online]. Available: https://doi.org/10.1016/S0893-6080(98)00140-3.
  12. Y. Yu, J. Chen, T. Gao, and M. Yu, “DAG-GNN: DAG Structure Learning with Graph Neural Networks,” 2019.
  13. A. E. W. Johnson et al., “MIMIC-III, a freely accessible critical care database,” Scientific Data, vol. 3, no. 1, p. 160035, 2016, , doi: 10.1038/sdata.2016.35.
  14. D. Maxwell Chickering and D. Heckerman, “Efficient Approximations for the Marginal Likelihood of Bayesian Networks with Hidden Variables,” Machine Learning, vol. 29, no. 2, pp. 181-212, 1997, , doi: 10.1023/A:1007469629108.
  15. G. W. Imbens and D. B. Rubin, Causal Inference for Statistics, Social, and Biomedical Sciences: An Introduction, Cambridge: Cambridge University Press, 2015, , doi: 10.1017/CBO9781139025751.
  16. L. Buesing et al., “Learning and Querying Fast Generative Models for Reinforcement Learning,” Feb. 2018, , doi: 10.48550/arXiv.1802.03006.
  17. S. Lachapelle, P. Brouillard, T. Deleu, and S. Lacoste-Julien, “Gradient-Based Neural DAG Learning,” 2020.
  18. M. Arenas-Martinez et al., “A Comparative Study of Data Storage and Processing Architectures for the Smart Grid,” in 2010 First IEEE International Conference on Smart Grid Communications, IEEE, Oct. 2010, pp. 285-290, , doi: 10.1109/smartgrid.2010.5622058.
  19. C. Deng, K. Bello, B. Aragam, and P. Ravikumar, “Optimizing NOTEARS Objectives via Topological Swaps,” 2023.
  20. N. Yin, T. Gao, Y. Yu, and Q. Ji, “Effective Causal Discovery under Identifiable Heteroscedastic Noise Model,” 2024.
  21. Q. Zhao, S. Wang, G. Bai, B. Pan, Z. Qin, and L. Zhao, “Deep Causal Generative Models with Property Control,” 2024.
  22. U. Hasan and M. O. Gani, “KCRL: A Prior Knowledge Based Causal Discovery Framework with Reinforcement Learning,” in Proceedings of the 7th Machine Learning for Healthcare Conference, Z. Lipton, R. Ranganath, M. Sendak, M. Sjoding, and S. Yeung, Eds., Proceedings of Machine Learning Research, vol. 182, PMLR, 2022, pp. 691-714.
  23. A. Poinsot, A. Leite, N. Chesneau, M. Sébag, and M. Schoenauer, “Learning Structural Causal Models through Deep Generative Models: Methods, Guarantees, and Challenges,” 2024.
  24. M. Zečević, D. S. Dhami, P. Veličković, and K. Kersting, “Relating Graph Neural Networks to Structural Causal Models,” 2021.
  25. M. Arenas-Martinez et al., “A Comparative Study of Data Storage and Processing Architectures for the Smart Grid,” in 2010 First IEEE International Conference on Smart Grid Communications, IEEE, Oct. 2010, pp. 285-290, , doi: 10.1109/smartgrid.2010.5622058.

    HOME

       - Conference
       - Journal
       - Paper Submission to Conference
       - Paper Submission to Journal
       - Fee Payment
       - For Authors
       - For Reviewers
       - Important Dates
       - Conference Committee
       - Editorial Board
       - Reviewers
       - Last Proceeding


    PROCEEDINGS

       - Volume 13, Issue 5 (ICAIIT 2025)
       - Volume 13, Issue 4 (ICAIIT 2025)
       - Volume 13, Issue 3 (ICAIIT 2025)
       - Volume 13, Issue 2 (ICAIIT 2025)
       - Volume 13, Issue 1 (ICAIIT 2025)
       - Volume 12, Issue 2 (ICAIIT 2024)
       - Volume 12, Issue 1 (ICAIIT 2024)
       - Volume 11, Issue 2 (ICAIIT 2023)
       - Volume 11, Issue 1 (ICAIIT 2023)
       - Volume 10, Issue 1 (ICAIIT 2022)
       - Volume 9, Issue 1 (ICAIIT 2021)
       - Volume 8, Issue 1 (ICAIIT 2020)
       - Volume 7, Issue 1 (ICAIIT 2019)
       - Volume 7, Issue 2 (ICAIIT 2019)
       - Volume 6, Issue 1 (ICAIIT 2018)
       - Volume 5, Issue 1 (ICAIIT 2017)
       - Volume 4, Issue 1 (ICAIIT 2016)
       - Volume 3, Issue 1 (ICAIIT 2015)
       - Volume 2, Issue 1 (ICAIIT 2014)
       - Volume 1, Issue 1 (ICAIIT 2013)


    LAST CONFERENCE

       ICAIIT 2026
         - Photos
         - Reports

    PAST CONFERENCES

    ETHICS IN PUBLICATIONS

    ACCOMODATION

    CONTACT US

 

        

         Proceedings of the International Conference on Applied Innovations in IT by Anhalt University of Applied Sciences is licensed under CC BY-SA 4.0


                                                   This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License


           ISSN 2199-8876
           Publisher: Edition Hochschule Anhalt
           Location: Anhalt University of Applied Sciences
           Email: leiterin.hsb@hs-anhalt.de
           Phone: +49 (0) 3496 67 5611
           Address: Building 01 - Red Building, Top floor, Room 425, Bernburger Str. 55, D-06366 Köthen, Germany

        site traffic counter

Creative Commons License
Except where otherwise noted, all works and proceedings on this site is licensed under Creative Commons Attribution-ShareAlike 4.0 International License.