mlsanityData to 14 Oct 2026

Estimating Causal Effects using a Multi-task Deep Ensemble

arXiv 2301.11351 ↗First posted 26 Jan 2023cs.LG stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

A number of methods have been proposed for causal effect estimation, yet few have demonstrated efficacy in handling data with complex structures, such as images. To fill this gap, we propose Causal Multi-task Deep Ensemble (CMDE), a novel framework that learns both shared and group-specific information from the study population. We provide proofs demonstrating equivalency of CDME to a multi-task Gaussian process (GP) with a coregionalization kernel a priori. Compared to multi-task GP, CMDE efficiently handles high-dimensional and multi-modal covariates and provides pointwise uncertainty estimates of causal effects. We evaluate our method across various types of datasets and tasks and find that CMDE outperforms state-of-the-art methods on a majority of these tasks.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 17 of its 44 references that are in the map. First posted on arXiv 26 Jan 2023.

Builds on

17 of 44 references.

References · 17

  1. 2017Deep Neural Networks as Gaussian Processescited by 622
  2. 2017Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learningcited by 478
  3. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 429
  4. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 410
  5. 2016Learning Representations for Counterfactual Inferencecited by 329
  6. 2018Gaussian Process Behaviour in Wide Deep Neural Networkscited by 317
  7. 2017Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processescited by 158
  8. 2018Deep Convolutional Networks as shallow Gaussian Processescited by 138
  9. 2017Automated versus do-it-yourself methods for causal inference: Lessons learned from a data analysis competitioncited by 106
  10. 2020COVID-19 Image Data Collection: Prospective Predictions Are the Futurecited by 100
  11. 2020Bayesian Deep Ensembles via the Neural Tangent Kernelcited by 90
  12. 2017Deep Counterfactual Networks with Propensity-Dropoutcited by 30
5 more
  1. 2021A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Modelscited by 29
  2. 2021Estimating Average Treatment Effects via Orthogonal Regularizationcited by 25
  3. 2020Valid Causal Inference with (Some) Invalid Instrumentscited by 19
  4. 2022Deep Multi-Modal Structural Equations For Causal Effect Estimation With Unstructured Proxiescited by 13
  5. 2022Incorporating Prior Knowledge into Neural Networks through an Implicit Composite Kernelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 2; 2025: 0; 2026: 2.

7 papers.

  1. 2023Causal Mediation Analysis with Multi-dimensional and Indirectly Observed Mediatorscited by 4
  2. 2024Causal-StoNet: Causal Inference for High-Dimensional Complex Datacited by 3
  3. 2023CATE Estimation With Potential Outcome Imputation From Local Regressioncited by 2
  4. 2023Estimating treatment effects from single-arm trials via latent-variable modelingcited by 1
  5. 2026Observationally Informed Adaptive Causal Experimental Designcited by 1
  6. 2024Enhancing predictive imaging biomarker discovery through treatment effect analysiscited by 0
  7. 2026Representation Learning for Sample-Efficient CATE Estimation by Leveraging Multiple Outcomescited by 0