mlsanityData to 7 Oct 2026

Disentangled Representation Learning for Causal Inference with Instruments

arXiv 2412.04641 ↗First posted 5 Dec 2024cs.LG cs.AI stat.MLcited by 6

Not on the map. Why?

Abstract (arXiv)

Latent confounders are a fundamental challenge for inferring causal effects from observational data. The instrumental variable (IV) approach is a practical way to address this challenge. Existing IV based estimators need a known IV or other strong assumptions, such as the existence of two or more IVs in the system, which limits the application of the IV approach. In this paper, we consider a relaxed requirement, which assumes there is an IV proxy in the system without knowing which variable is the proxy. We propose a Variational AutoEncoder (VAE) based disentangled representation learning method to learn an IV representation from a dataset with latent confounders and then utilise the IV representation to obtain an unbiased estimation of the causal effect from the data. Extensive experiments on synthetic and real-world data have demonstrated that the proposed algorithm outperforms the existing IV based estimators and VAE-based estimators.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 25 of its 59 references that are in the map. First posted on arXiv 5 Dec 2024.

Builds on

25 of 59 references.

References · 25

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2019An Introduction to Variational Autoencoderscited by 997
  3. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 929
  4. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  5. 2017Causal Effect Inference with Deep Latent-Variable Modelscited by 408
  6. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  7. 2016Learning Representations for Counterfactual Inferencecited by 327
  8. 2016Generalized Random Forestscited by 309
  9. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  10. 2016Identifying Causal Effects With Proxy Variables of an Unmeasured Confoundercited by 138
  11. 2019Kernel Instrumental Variable Regressioncited by 118
  12. 2020An Introduction to Proximal Causal Learningcited by 91
13 more
  1. 2019Deep Generalized Method of Moments for Instrumental Variable Analysiscited by 88
  2. 2020Treatment effect estimation with disentangled latent factorscited by 63
  3. 2019Machine Learning Estimation of Heterogeneous Treatment Effects with Instrumentscited by 29
  4. 2021A Critical Look at the Consistency of Causal Estimation With Deep Latent Variable Modelscited by 29
  5. 2013On the Testability of Causal Models with Latent and Instrumental Variablescited by 26
  6. 2014Instrumental Variables Estimation with Some Invalid Instruments and its Application to Mendelian Randomizationcited by 22
  7. 2019A semiparametric instrumental variable approach to optimal treatment regimes under endogeneitycited by 22
  8. 2020Valid Causal Inference with (Some) Invalid Instrumentscited by 19
  9. 2022Data-Driven Causal Effect Estimation Based on Graphical Causal Modelling: A Surveycited by 19
  10. 2021Auto IV: Counterfactual Prediction via Automatic Instrumental Variable Decompositioncited by 18
  11. 2020Ivy: Instrumental Variable Synthesis for Causal Inferencecited by 17
  12. 2018Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysiscited by 6
  13. 2022Ancestral Instrument Method for Causal Inference without Complete Knowledgecited by 6

Built on by

Cited by year (2026 to 7 Oct)

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

6 papers.

  1. 2025Causal Prompting for Implicit Sentiment Analysis with Large Language Modelscited by 4
  2. 2025Causal Effect Estimation under Networked Interference without Networked Unconfoundedness Assumptioncited by 1
  3. 2025FairDRL-ST: Disentangled Representation Learning for Fair Spatio-Temporal Mobility Predictioncited by 1
  4. 2026When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generationcited by 1
  5. 2026Towards causal effect estimation with learned instrument representationscited by 0
  6. 2026Addressing Instrument-Outcome Confounding in Mendelian Randomization through Representation Learningcited by 0