摘要
Estimating the average treatment effect (ATE) from observational data is challenging due to selection bias. Existing works mainly tackle this challenge in two ways. Some researchers propose constructing a score function that satisfies the orthogonal condition, which guarantees that the established ATE estimator is "orthogonal" to be more robust. The others explore representation learning models to achieve a balanced representation between the treated and the controlled groups. However, existing studies fail to 1) discriminate treated units from controlled ones in the representation space to avoid the over-balanced issue; 2) fully utilize the "orthogonality information". In this paper, we propose a moderately-balanced representation learning (MBRL) framework based on recent covariates balanced representation learning methods and orthogonal machine learning theory. This framework protects the representation from being over-balanced via multi-task learning. Simultaneously, MBRL incorporates the noise orthogonality information in the training and validation stages to achieve a better ATE estimation. The comprehensive experiments on benchmark and simulated datasets show the superiority and robustness of our method on treatment effect estimations compared with existing state-of-the-art methods.
学科与关键词
- Robust Causal Learning for the Estimation of Average Treatment EffectsHuang, Yiyan; Leung, Cheuk Hang; Wu, Qi*; Yan, Xing; Ma, Shumin; Yuan, Zhiri; Wang, Dongdong; Huang, ZhixiangIEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC), Padua, ITALY, 2022-07-18 To 2022-07-23.
- Identification and Auto-Debiased Machine Learning for Outcome-Conditioned Average Structural DerivativesJin, Zequn; Lin, Lihua; Zhang, Zhengyu*JOURNAL OF BUSINESS & ECONOMIC STATISTICS, 2024.
- Causal Mediation Analysis with Hidden ConfoundersCheng, Lu*; Guo, Ruocheng; Liu, Huan15th ACM International Conference on Web Search and Data Mining (WSDM), ELECTR NETWORK, 2022-02-21 To 2022-02-25.被引 3
