Self-Distilled Disentangled Learning for Counterfactual Prediction
This work addresses the problem of improving counterfactual inference accuracy for researchers in causal machine learning, though it appears incremental as it builds on existing disentanglement methods.
The paper tackles the challenge of achieving independent disentangled representations for counterfactual prediction by proposing the Self-Distilled Disentanglement (SD^2) framework, which avoids complex mutual information estimators and shows effectiveness in experiments on synthetic and real-world datasets with observed and unobserved confounders.
The advancements in disentangled representation learning significantly enhance the accuracy of counterfactual predictions by granting precise control over instrumental variables, confounders, and adjustable variables. An appealing method for achieving the independent separation of these factors is mutual information minimization, a task that presents challenges in numerous machine learning scenarios, especially within high-dimensional spaces. To circumvent this challenge, we propose the Self-Distilled Disentanglement framework, referred to as $SD^2$. Grounded in information theory, it ensures theoretically sound independent disentangled representations without intricate mutual information estimator designs for high-dimensional representations. Our comprehensive experiments, conducted on both synthetic and real-world datasets, confirms the effectiveness of our approach in facilitating counterfactual inference in the presence of both observed and unobserved confounders.