Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Disentangled Representation for Causal Mediation Analysis (2302.09694v2)

Published 19 Feb 2023 in cs.LG and stat.ME

Abstract: Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions. Causal mediation analysis is a method that is often used to reveal direct and indirect effects. Deep learning shows promise in mediation analysis, but the current methods only assume latent confounders that affect treatment, mediator and outcome simultaneously, and fail to identify different types of latent confounders (e.g., confounders that only affect the mediator or outcome). Furthermore, current methods are based on the sequential ignorability assumption, which is not feasible for dealing with multiple types of latent confounders. This work aims to circumvent the sequential ignorability assumption and applies the piecemeal deconfounding assumption as an alternative. We propose the Disentangled Mediation Analysis Variational AutoEncoder (DMAVAE), which disentangles the representations of latent confounders into three types to accurately estimate the natural direct effect, natural indirect effect and total effect. Experimental results show that the proposed method outperforms existing methods and has strong generalisation ability. We further apply the method to a real-world dataset to show its potential application.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. Mostly harmless econometrics: An empiricist’s companion. Princeton University Press.
  2. The moderator–mediator variable distinction in social psychological research: Conceptual, strategic, and statistical considerations. Journal of Personality and Social Psychology, 51(6): 1173–1182.
  3. Sex bias in graduate admissions: Data from Berkeley: Measuring bias is harder than is usually assumed, and the evidence is sometimes contrary to expectation. Science, 187(4175): 398–404.
  4. Pyro: Deep universal probabilistic programming. Journal of Machine Learning Research, 1–6.
  5. The causalweight package for causal inference in R.
  6. Bollen, K. A. 1989. Structural equations with latent variables, volume 210. John Wiley & Sons.
  7. Causal Mediation Analysis with Hidden Confounders. In The Fifteenth ACM International Conference on Web Search and Data Mining, WSDM 2022, 113–122.
  8. UCI Machine Learning Repository.
  9. A survey of learning causality with data: Problems and methods. ACM Computing Surveys (CSUR), 53(4): 1–37.
  10. Holland, P. W. 1988. Causal inference, path analysis and recursive structural equations models. ETS Research Report Series, 1988(1): 1–50.
  11. Huber, M. 2014. Identifying causal mechanisms (primarily) based on inverse probability weighting. Journal of Applied Econometrics, 29(6): 920–943.
  12. The finite sample performance of estimators for mediation analysis under sequential conditional independence. Journal of Business & Economic Statistics, 34(1): 139–160.
  13. A general approach to causal mediation analysis. Psychological Methods, 15(4): 309–334.
  14. Causal analysis: Assumptions, models, and data. Beverly Hills (Calif.): Sage, 1983.
  15. Process analysis: Estimating mediation in treatment evaluations. Evaluation Review, 5(5): 602–619.
  16. Auto-Encoding Variational Bayes. In 2nd International Conference on Learning Representations, ICLR 2014, 1–14.
  17. A simple unified approach for estimating natural direct and indirect effects. American Journal of Epidemiology, 176(3): 190–195.
  18. Causal Effect Inference with Deep Latent-Variable Models. In Advances in Neural Information Processing Systems 30, NeurIPS 2017, 6446–6456.
  19. MacKinnon, D. P. 2012. Introduction to statistical mediation analysis. Routledge.
  20. Estimating mediated effects in prevention studies. Evaluation Review, 17(2): 144–158.
  21. Mediation analysis. Annual Review of Psychology, 58: 1–22.
  22. Pytorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, NeurIPS 2019, 8024–8035.
  23. Pearl, J. 2009a. Causal inference in statistics: An overview. Statistics Surveys, 3: 96–146.
  24. Pearl, J. 2009b. Causality. Cambridge University Press.
  25. Pearl, J. 2014. Interpretation and identification of causal mediation. Psychological Methods, 19(4): 459–481.
  26. Identifiability and exchangeability for direct and indirect effects. Epidemiology, 143–155.
  27. Estimation of regression coefficients when some regressors are not always observed. Journal of the American Statistical Association, 89(427): 846–866.
  28. Rubin, D. B. 1974. Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5): 688.
  29. Rubin, D. B. 2005. Causal inference using potential outcomes: Design, modeling, decisions. Journal of the American Statistical Association, 100(469): 322–331.
  30. Causal mediation analysis with observational data: considerations and illustration examining mechanisms linking neighborhood poverty to adolescent substance use. American Journal of Epidemiology, 188(3): 598–608.
  31. Medflex: an R package for flexible mediation analysis using natural effect models. Journal of Statistical Software, 76: 1–46.
  32. Mediation: R package for causal mediation analysis.
  33. VanderWeele, T. J. 2016. Mediation analysis: a practitioner’s guide. Annual Review of Public Health, 37: 17–32.
  34. Wright, S. 1934. The method of path coefficients. The Annals of Mathematical Statistics, 5(3): 161–215.
  35. The Identification and Estimation of Direct and Indirect Effects in A/B Tests through Causal Mediation Analysis. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, 2989–2999.
  36. Causal modeling-based discrimination discovery and removal: criteria, bounds, and algorithms. IEEE Transactions on Knowledge and Data Engineering, 31(11): 2035–2050.
  37. Treatment Effect Estimation with Disentangled Latent Factors. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, 10923–10930.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now