MetaCI: Meta-Learning for Causal Inference in a Heterogeneous Population
This work addresses causal inference challenges in fields like healthcare and education where data comes from heterogeneous populations, but it is incremental as it builds on existing meta-learning and causal inference techniques.
The paper tackles the problem of performing causal inference in heterogeneous populations with multiple subgroups, proposing the MetaCI framework to answer counterfactual questions by addressing distribution shifts. It demonstrates that meta initialization reduces mean absolute percentage error for average treatment effect compared to random initialization and other methods.
Performing inference on data obtained through observational studies is becoming extremely relevant due to the widespread availability of data in fields such as healthcare, education, retail, etc. Furthermore, this data is accrued from multiple homogeneous subgroups of a heterogeneous population, and hence, generalizing the inference mechanism over such data is essential. We propose the MetaCI framework with the goal of answering counterfactual questions in the context of causal inference (CI), where the factual observations are obtained from several homogeneous subgroups. While the CI network is designed to generalize from factual to counterfactual distribution in order to tackle covariate shift, MetaCI employs the meta-learning paradigm to tackle the shift in data distributions between training and test phase due to the presence of heterogeneity in the population, and due to drifts in the target distribution, also known as concept shift. We benchmark the performance of the MetaCI algorithm using the mean absolute percentage error over the average treatment effect as the metric, and demonstrate that meta initialization has significant gains compared to randomly initialized networks, and other methods.