Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
This addresses the challenge of evaluating treatment effectiveness in new patient populations with limited data and different covariates, which is incremental as it adapts existing CATE methods to heterogeneous transfer learning.
The paper tackles the problem of estimating conditional average treatment effects (CATE) in a target domain by transferring knowledge from a source domain with different feature spaces, using representation learning and a multi-task architecture. It demonstrates performance improvements on a semi-synthetic benchmark, providing insights into different learners from a transfer perspective.
Consider the problem of improving the estimation of conditional average treatment effects (CATE) for a target domain of interest by leveraging related information from a source domain with a different feature space. This heterogeneous transfer learning problem for CATE estimation is ubiquitous in areas such as healthcare where we may wish to evaluate the effectiveness of a treatment for a new patient population for which different clinical covariates and limited data are available. In this paper, we address this problem by introducing several building blocks that use representation learning to handle the heterogeneous feature spaces and a flexible multi-task architecture with shared and private layers to transfer information between potential outcome functions across domains. Then, we show how these building blocks can be used to recover transfer learning equivalents of the standard CATE learners. On a new semi-synthetic data simulation benchmark for heterogeneous transfer learning we not only demonstrate performance improvements of our heterogeneous transfer causal effect learners across datasets, but also provide insights into the differences between these learners from a transfer perspective.