CAETC: Causal Autoencoding and Treatment Conditioning for Counterfactual Estimation over Time
This addresses a key problem in fields like personalized medicine by providing a more accurate method for counterfactual estimation over time, though it appears incremental as it builds on adversarial representation learning and existing architectures.
The paper tackles the challenge of time-dependent confounding bias in counterfactual estimation over time, such as in personalized medicine, by introducing CAETC, a method that uses causal autoencoding and treatment conditioning to achieve significant improvement in accuracy over existing methods.
Counterfactual estimation over time is important in various applications, such as personalized medicine. However, time-dependent confounding bias in observational data still poses a significant challenge in achieving accurate and efficient estimation. We introduce causal autoencoding and treatment conditioning (CAETC), a novel method for this problem. Built on adversarial representation learning, our method leverages an autoencoding architecture to learn a partially invertible and treatment-invariant representation, where the outcome prediction task is cast as applying a treatment-specific conditioning on the representation. Our design is independent of the underlying sequence model and can be applied to existing architectures such as long short-term memories (LSTMs) or temporal convolution networks (TCNs). We conduct extensive experiments on synthetic, semi-synthetic, and real-world data to demonstrate that CAETC yields significant improvement in counterfactual estimation over existing methods.