Estimating treatment effects from irregular time series observations with hidden confounders
AUTHORs: 
Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, Yan LiuAuthors Info & Claims
Defu Cao, James Enouen, Yujing Wang, Xiangchen Song, Chuizheng Meng, Hao Niu, Yan LiuAuthors Info & ClaimsArticle No.: 775, Pages 6897 - 6905
Abstract
Causal analysis for time series data, in particular estimating individualized treatment effect (ITE), is a key task in many real-world applications, such as finance, retail, healthcare, etc. Real-world time series can include large-scale, irregular, and intermittent time series observations, raising significant challenges to existing work attempting to estimate treatment effects. Specifically, the existence of hidden confounders can lead to biased treatment estimates and complicate the causal inference process. In particular, anomaly hidden confounders which exceed the typical range can lead to high variance estimates. Moreover, in continuous time settings with irregular samples, it is challenging to directly handle the dynamics of causality. In this paper, we leverage recent advances in Lip-schitz regularization and neural controlled differential equations (CDE) to develop an effective and scalable solution, namely LipCDE, to address the above challenges. LipCDE can directly model the dynamic causal relationships between historical data and outcomes with irregular samples by considering the boundary of hidden confounders given by Lipschitz constrained neural networks. Furthermore, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate the effectiveness and scalability of LipCDE.
References
[1]
Abadie, A.; Diamond, A.; and Hainmueller, J. 2010. Synthetic control methods for comparative case studies: Estimating the effect of California's tobacco control program. Journal of the American statistical Association, 105(490): 493-505.
[2]
Araujo, A.; Negrevergne, B.; Chevaleyre, Y.; and Atif, J. 2021. On Lipschitz Regularization of Convolutional Layers using Toeplitz Matrix Theory. Thirty-Fifth AAAI Conference on Artificial Intelligence.
[3]
Bahadori, M. T.; and Heckerman, D. 2021. Debiasing Concept-based Explanations with Causal Analysis. In International Conference on Learning Representations.
[4]
Bellot, A.; and Van Der Schaar, M. 2021. Policy analysis using synthetic controls in continuous-time. In International Conference on Machine Learning, 759-768. PMLR.
[5]
Berrevoets, J.; Jordon, J.; Bica, I.; Gimson, A.; and van der Schaar, M. 2020. OrganITE: Optimal transplant donor organ offering using an individual treatment effect. https://proceedings.neurips.cc/paper/2020, 33.
[6]
B'ethune, L.; Gonz'alez-Sanz, A.; Mamalet, F.; and Serrurier, M. 2021. The Many Faces of 1-Lipschitz Neural Networks. ArXiv, abs/2104.05097.
[7]
Bica, I.; Alaa, A.; and Van Der Schaar, M. 2020. Time series deconfounder: Estimating treatment effects over time in the presence of hidden confounders. In International Conference on Machine Learning, 884-895. PMLR.
[8]
Bica, I.; Alaa, A. M.; Jordon, J.; and van der Schaar, M. 2020. Estimating counterfactual treatment outcomes over time through adversarially balanced representations. In International Conference on Learning Representations.
[9]
Brodersen, K. H.; Gallusser, F.; Koehler, J.; Remy, N.; and Scott, S. L. 2015. Inferring causal impact using Bayesian structural time-series models. The Annals of Applied Statistics, 9(1): 247-274.
[10]
Cao, D.; Li, J.; Ma, H.; and Tomizuka, M. 2021. Spectral temporal graph neural network for trajectory prediction. In 2021 IEEE International Conference on Robotics and Automation (ICRA), 1839-1845. IEEE.
[11]
Cao, D.; Wang, Y.; Duan, J.; Zhang, C.; Zhu, X.; Huang, C.; Tong, Y.; Xu, B.; Bai, J.; Tong, J.; et al. 2020. Spectral temporal graph neural network for multivariate time-series forecasting. Advances in neural information processing systems, 33: 17766-17778.
[12]
Chen, R. T.; Rubanova, Y.; Bettencourt, J.; and Duvenaud, D. 2018. Neural ordinary differential equations. arXiv preprint arXiv:1806.07366.
[13]
Curth, A.; and van der Schaar, M. 2021. On Inductive Biases for Heterogeneous Treatment Effect Estimation. arXiv preprint arXiv:2106.03765.
[14]
D'Acunto, G.; Bajardi, P.; Bonchi, F.; and De Francisci Morales, G. 2021. The evolving causal structure of equity risk factors. In Proceedings of the Second ACM International Conference on AI in Finance, 1-8.
[15]
D'Amour, A. 2019. On Multi-Cause Causal Inference with Unobserved Confounding: Counterexamples, Impossibility, and Alternatives. ArXiv, abs/1902.10286.
[16]
De Brouwer, E.; Gonzalez, J.; and Hyland, S. 2022. Predicting the impact of treatments over time with uncertainty aware neural differential equations. In International Conference on Artificial Intelligence and Statistics, 4705-4722. PMLR.
[17]
Erichson, N. B.; Azencot, O.; Queiruga, A.; Hodgkinson, L.; and Mahoney, M. W. 2020. Lipschitz recurrent neural networks. arXiv preprint arXiv:2006.12070.
[18]
Fröhlich, F.; Loos, C.; and Hasenauer, J. 2019. Scalable inference of ordinary differential equation models of biochemical processes. Gene Regulatory Networks, 385-422.
[19]
Gao, T.; Subramanian, D.; Bhattacharjya, D.; Shou, X.; Mattei, N.; and Bennett, K. P. 2021. Causal inference for event pairs in multivariate point processes. Advances in Neural Information Processing Systems, 34: 17311-17324.
[20]
Gouk, H.; Frank, E.; Pfahringer, B.; and Cree, M. J. 2021. Regularisation of neural networks by enforcing lipschitz continuity. Machine Learning, 110(2): 393-416.
[21]
Guo, R.; Li, J.; and Liu, H. 2020a. Counterfactual evaluation of treatment assignment functions with networked observational data. In Proceedings of the 2020 SIAM International Conference on Data Mining, 271-279. SIAM.
[22]
Guo, R.; Li, J.; and Liu, H. 2020b. Learning individual causal effects from networked observational data. In Proceedings of the 13th International Conference on Web Search and Data Mining, 232-240.
[23]
Hatt, T.; and Feuerriegel, S. 2021. Sequential Deconfounding for Causal Inference with Unobserved Confounders. arXiv preprint arXiv:2104.09323.
[24]
Hernán, M. A.; and Robins, J. M. 2010. Causal inference: What If. CRC Boca Raton, FL.
[25]
Imai, K.; and Van Dyk, D. A. 2004. Causal inference with general treatment regimes: Generalizing the propensity score. Journal of the American Statistical Association, 99(467): 854-866.
[26]
Johansson, F.; Shalit, U.; and Sontag, D. 2016. Learning representations for counterfactual inference. In International conference on machine learning, 3020-3029. PMLR.
[27]
Johnson, A. E.; Pollard, T. J.; Shen, L.; Li-Wei, H. L.; Feng, M.; Ghassemi, M.; Moody, B.; Szolovits, P.; Celi, L. A.; and Mark, R. G. 2016. MIMIC-III, a freely accessible critical care database. Scientific data, 3(1): 1-9.
[28]
Kallus, N.; Mao, X.; and Udell, M. 2018. Causal inference with noisy and missing covariates via matrix factorization. arXiv preprint arXiv:1806.00811.
[29]
Kidger, P.; Morrill, J.; Foster, J.; and Lyons, T. 2020. Neural controlled differential equations for irregular time series. arXiv preprint arXiv:2005.08926.
[30]
Kuroki, M.; and Pearl, J. 2014. Measurement bias and effect restoration in causal inference. Biometrika, 101(2): 423-437.
[31]
Kuzmanovic, M.; Hatt, T.; and Feuerriegel, S. 2021. De-confounding Temporal Autoencoder: estimating treatment effects over time using noisy proxies. In Machine Learning for Health, 143-155. PMLR.
[32]
Langley, P. 2000. Crafting Papers on Machine Learning. In Langley, P., ed., Proceedings of the 17th International Conference on Machine Learning (ICML 2000), 1207-1216. Stanford, CA: Morgan Kaufmann.
[33]
Lim, B.; Alaa, A.; and van der Schaar, M. 2018. Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks. NeurIPS, 18: 7483-7493.
[34]
Liu, R.; Yin, C.; and Zhang, P. 2020. Estimating individual treatment effects with time-varying confounders. In 2020 IEEE International Conference on Data Mining (ICDM), 382-391. IEEE.
[35]
Ma, J.; Guo, R.; Chen, C.; Zhang, A.; and Li, J. 2021. Decon-founding with Networked Observational Data in a Dynamic Environment. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 166-174.
[36]
Mandel, T.; Liu, Y.-E.; Levine, S.; Brunskill, E.; and Popovic, Z. 2014. Offline policy evaluation across representations with applications to educational games. In AAMAS, volume 1077.
[37]
Mastakouri, A. A.; Schölkopf, B.; and Janzing, D. 2021. Necessary and sufficient conditions for causal feature selection in time series with latent common causes. In Meila, M.; and Zhang, T., eds., Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learning Research, 7502-7511. PMLR.
[38]
Ogburn, E. L.; Shpitser, I.; and Tchetgen, E. J. T. 2020. Counterexamples to" the blessings of multiple causes" by wang and blei. arXiv preprint arXiv:2001.06555.
[39]
Pearl, J. 2012. On measurement bias in causal inference. arXiv preprint arXiv:1203.3504.
[40]
Pearl, J.; et al. 2000. Causality: Models, reasoning and inference. Cambridge, UK: Cambridge University Press, 19.
[41]
Perugachi-Diaz, Y.; Tomczak, J. M.; and Bhulai, S. 2021. Invertible DenseNets with Concatenated LipSwish. In Beygelzimer, A.; Dauphin, Y.; Liang, P.; and Vaughan, J. W., eds., Advances in Neural Information Processing Systems.
[42]
Robins, J. M.; and Hernán, M. A. 2009. Estimation of the causal effects of time-varying exposures. Longitudinal data analysis, 553: 599.
[43]
Robins, J. M.; Hernán, M. A.; and Brumback, B. 2000. Marginal Structural Models and Causal Inference in Epidemiology. Epidemiology, 11(5): 551.
[44]
Roy, J.; Lum, K. J.; and Daniels, M. J. 2017. A Bayesian nonparametric approach to marginal structural models for point treatments and a continuous or survival outcome. Biostatistics, 18(1): 32-47.
[45]
Schulam, P.; and Saria, S. 2017. Reliable decision support using counterfactual models. Advances in Neural Information Processing Systems, 30: 1697-1708.
[46]
Seedat, N.; Imrie, F.; Bellot, A.; Qian, Z.; and van der Schaar, M. 2022. Continuous-Time Modeling of Counterfactual Outcomes Using Neural Controlled Differential Equations. arXiv preprint arXiv:2206.08311.
[47]
Shalit, U.; Johansson, F. D.; and Sontag, D. 2017. Estimating individual treatment effect: generalization bounds and algorithms. In International Conference on Machine Learning, 3076-3085. PMLR.
[48]
Simpson, E. H. 1951. The interpretation of interaction in contingency tables. Journal of the Royal Statistical Society: Series B (Methodological), 13(2): 238-241.
[49]
Soleimani, H.; Subbaswamy, A.; and Saria, S. 2017. Treatment-response models for counterfactual reasoning with continuous-time, continuous-valued interventions. arXiv preprint arXiv:1704.02038.
[50]
Steiger, E.; Mußgnug, T.; and Kroll, L. E. 2020. Causal analysis of COVID-19 observational data in German districts reveals effects of mobility, awareness, and temperature. medRxiv, 2020-07.
[51]
Veitch, V.; Sridhar, D.; and Blei, D. 2020. Adapting text embeddings for causal inference. In Conference on Uncertainty in Artificial Intelligence, 919-928. PMLR.
[52]
Wang, Y.; and Blei, D. M. 2019. The blessings of multiple causes. Journal of the American Statistical Association, 114(528): 1574-1596.
[53]
Ware, A. F. 1998. Fast approximate Fourier transforms for irregularly spaced data. SIAM review, 40(4): 838-856.
[54]
Zhang, Y.; Cao, D.; and Liu, Y. 2022. Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media. In Advances in Neural Information Processing Systems.
[55]
Zheng, J.; D'Amour, A.; and Franks, A. 2021. Bayesian Inference and Partial Identification in Multi-Treatment Causal Inference with Unobserved Confounding. arXiv preprint arXiv:2111.07973.
[56]
Zibelman, M.; Ramamurthy, C.; and Plimack, E. R. 2016. Emerging role of immunotherapy in urothelial carcinoma—advanced disease. In Urologic Oncology: Seminars and Original Investigations, volume 34, 538-547. Elsevier.
Recommendations
Causal Mediation Analysis with Hidden Confounders
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningAn important problem in causal inference is to break down the total effect of a treatment on an outcome into different causal pathways and to quantify the causal effect in each pathway. For instance, in causal fairness, the total effect of being a male ...
Causal discovery with hidden confounders using the algorithmic Markov condition
UAI '23: Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial IntelligenceCausal sufficiency is a cornerstone assumption in causal discovery. It is, however, both unlikely to hold in practice as well as unverifiable. When it does not hold, existing methods struggle to return meaningful results. In this paper, we show how to ...
Estimating causal effects by bounding confounding
UAI'14: Proceedings of the Thirtieth Conference on Uncertainty in Artificial IntelligenceAssessing the causal effect of a treatment variable X on an outcome variable Y is usually difficult due to the existence of unobserved common causes. Without further assumptions, observed dependences do not even prove the existence of a causal effect ...
Comments
Information & Contributors
Information
Published In
Copyright © 2023 Association for the Advancement of Artificial Intelligence.
Sponsors
- Association for the Advancement of Artificial Intelligence
Publisher
AAAI Press
Publication History
Published: 07 February 2023
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 30 Aug 2024