Cycle-Balanced Representation Learning For Counterfactual Inference
This work addresses counterfactual inference for domains like healthcare and advertising, offering a novel method to handle observational data limitations, though it builds on existing representation learning techniques.
The paper tackles the problem of learning counterfactual effects from observational data, which suffers from missing outcomes and distribution discrepancies, by proposing a Cycle-Balanced Representation Learning framework (CBRE) that achieves state-of-the-art performance on three real-world datasets.
With the widespread accumulation of observational data, researchers obtain a new direction to learn counterfactual effects in many domains (e.g., health care and computational advertising) without Randomized Controlled Trials(RCTs). However, observational data suffer from inherent missing counterfactual outcomes, and distribution discrepancy between treatment and control groups due to behaviour preference. Motivated by recent advances of representation learning in the field of domain adaptation, we propose a novel framework based on Cycle-Balanced REpresentation learning for counterfactual inference (CBRE), to solve above problems. Specifically, we realize a robust balanced representation for different groups using adversarial training, and meanwhile construct an information loop, such that preserve original data properties cyclically, which reduces information loss when transforming data into latent representation space.Experimental results on three real-world datasets demonstrate that CBRE matches/outperforms the state-of-the-art methods, and it has a great potential to be applied to counterfactual inference.