An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

2025-10-28

AI Summary

This paper addresses the challenges of substantial confounding bias and poor generalization across interventions in causal effect estimation under unobserved confounding. We propose a causal inference framework based on outcome-invariant data augmentation. Methodologically, we innovatively treat data augmentation as an instrumental-variable-like (IV-like) mechanism, enabling IV-style regression without requiring genuine instrumental variables; support compositional augmentation to emulate worst-case interventions, thereby enhancing robustness; and establish theoretical consistency at the population level. We further provide analytical guarantees for linear models and validate the approach through extensive simulations and real-world experiments. Results demonstrate that our method significantly reduces confounding bias, improves estimation accuracy of causal effects, and enhances out-of-distribution predictive performance across diverse interventions.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Computer Vision: Adversarial Attacks & Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i.i.d. setting, but for generalization across interventions as well. Specifically, we argue that when the outcome generating mechanism is invariant to our choice of DA, then such augmentations can effectively be thought of as interventions on the treatment generating mechanism itself. This can potentially help to reduce bias in causal effect estimation arising from hidden confounders. In the presence of such unobserved confounding we typically make use of instrumental variables (IVs) -- sources of treatment randomization that are conditionally independent of the outcome. However, IVs may not be as readily available as DA for many applications, which is the main motivation behind this work. By appropriately regularizing IV based estimators, we introduce the concept of IV-like (IVL) regression for mitigating confounding bias and improving predictive performance across interventions even when certain IV properties are relaxed. Finally, we cast parameterized DA as an IVL regression problem and show that when used in composition can simulate a worst-case application of such DA, further improving performance on causal estimation and generalization tasks beyond what simple DA may offer. This is shown both theoretically for the population case and via simulation experiments for the finite sample case using a simple linear example. We also present real data experiments to support our case.

Problem

• Estimating causal effects with hidden confounders bias
• Using data augmentation as interventions to reduce bias
• Developing IV-like regression for improved causal generalization

Innovation

• Outcome-invariant data augmentation as interventions
• IV-like regression mitigates unobserved confounding bias
• Parameterized DA simulates worst-case scenarios for generalization