mlsanityData to 7 Oct 2026

Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxies

arXiv 2203.09672 ↗First posted 18 Mar 2022cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

Estimating the effect of intervention from observational data while accounting for confounding variables is a key task in causal inference. Oftentimes, the confounders are unobserved, but we have access to large amounts of additional unstructured data (images, text) that contain valuable proxy signal about the missing confounders. This paper argues that leveraging this unstructured data can greatly improve the accuracy of causal effect estimation. Specifically, we introduce deep multi-modal structural equations, a generative model for causal effect estimation in which confounders are latent variables and unstructured data are proxy variables. This model supports multiple multi-modal proxies (images, text) as well as missing data. We empirically demonstrate that our approach outperforms existing methods based on propensity scores and corrects for confounding using unstructured inputs on tasks in genomics and healthcare. Our methods can potentially support the use of large amounts of data that were previously not used in causal inference

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 25 of its 70 references that are in the map. First posted on arXiv 18 Mar 2022.

Builds on

25 of 70 references.

References · 25

  1. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,841
  2. 2016Variational Inference: A Review for Statisticianscited by 1,466
  3. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 426
  4. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  5. 2016Learning Representations for Counterfactual Inferencecited by 327
  6. 2019Adapting Neural Networks for the Estimation of Treatment Effectscited by 285
  7. 2020Deep Structural Causal Models for Tractable Counterfactual Inferencecited by 210
  8. 2021Towards Causal Representation Learningcited by 207
  9. 2018Multimodal Generative Models for Scalable Weakly-Supervised Learningcited by 200
  10. 2018The Blessings of Multiple Causescited by 103
  11. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  12. 2019Support and Invertibility in Domain-Invariant Representationscited by 87
13 more
  1. 2022CLIP-Event: Connecting Text and Images with Event Structurescited by 86
  2. 2020Treatment effect estimation with disentangled latent factorscited by 63
  3. 2018How to Make Causal Inferences Using Textscited by 59
  4. 2020Counterfactual Fairness with Disentangled Causal Effect Variational Autoencodercited by 45
  5. 2018DeepMatch: Balancing Deep Covariate Representations for Causal Inference Using Adversarial Trainingcited by 42
  6. 2018Learning Weighted Representations for Generalization Across Designscited by 41
  7. 2020Causal Effects of Linguistic Propertiescited by 39
  8. 2019Using Embeddings to Correct for Unobserved Confounding in Networkscited by 31
  9. 2017Implicit Causal Models for Genome-wide Association Studiescited by 10
  10. 2020MissDeepCausal: Causal Inference from Incomplete Data Using Deep Latent Variable Modelscited by 7
  11. 2020Targeted VAE: Variational and Targeted Learning for Causal Inferencecited by 7
  12. 2016Counterfactual Prediction with Deep Instrumental Variables Networkscited by 4
  13. 2021Towards Principled Causal Effect Estimation by Deep Identifiable Modelscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 5; 2024: 4; 2025: 2; 2026: 1.

13 papers.

Sort:

By area:

  1. 2024Simple and Effective Masked Diffusion Language Modelscited by 800
  2. 2023Diffusion Models With Learned Adaptive Noisecited by 50
  3. 2023ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representationcited by 13
  4. 2022Deep Causal Learning: Representation, Discovery and Inferencecited by 11
  5. 2023Patchwork Learning: A Paradigm Towards Integrative Analysis across Diverse Biomedical Data Sourcescited by 10
  6. 2023Estimating Causal Effects using a Multi-task Deep Ensemblecited by 7
  7. 2024Towards the Causal Complete Cause of Multi-Modal Representation Learningcited by 5
  8. 2023Calibrated and Conformal Propensity Scores for Causal Effect Estimationcited by 3
  9. 2024Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriorscited by 2
  10. 2025LLM-Driven Treatment Effect Estimation Under Inference Time Text Confoundingcited by 2
  11. 2024Recovering Latent Confounders from High-dimensional Proxy Variablescited by 0
  12. 2025Causal Prompt Calibration Guided Segment Anything Model for Open-Vocabulary Multi-Entity Segmentationcited by 0
1 more
  1. 2026Robust Multimodal Representation Learning in Healthcarecited by 0