Self Balancing Neural Network: A Novel Method to Estimate Average Treatment Effect

2025-07-17

AI Summary

In observational studies, confounding variables and invalid instrumental variables often bias average treatment effect (ATE) estimation, while conventional propensity score–based methods are sensitive to model misspecification. To address these challenges, we propose the Self-Balancing Neural Network (SBNN), a one-stage, end-to-end deep learning framework for causal effect estimation. SBNN employs a dedicated balancing network to implicitly learn pseudo-propensity scores—circumventing explicit modeling assumptions—and incorporates a multi-pseudo-propensity-score mechanism to enhance estimation stability. Furthermore, it integrates a deep feedforward architecture with a multi-task learning objective to improve generalizability across heterogeneous populations. Extensive experiments on diverse synthetic benchmarks and real-world datasets demonstrate that SBNN consistently outperforms state-of-the-art baselines, yielding significantly more accurate and robust ATE estimates under both mild and severe confounding scenarios.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

In observational studies, confounding variables affect both treatment and outcome. Moreover, instrumental variables also influence the treatment assignment mechanism. This situation sets the study apart from a standard randomized controlled trial, where the treatment assignment is random. Due to this situation, the estimated average treatment effect becomes biased. To address this issue, a standard approach is to incorporate the estimated propensity score when estimating the average treatment effect. However, these methods incur the risk of misspecification in propensity score models. To solve this issue, a novel method called the "Self balancing neural network" (Sbnet), which lets the model itself obtain its pseudo propensity score from the balancing net, is proposed in this study. The proposed method estimates the average treatment effect by using the balancing net as a key part of the feedforward neural network. This formulation resolves the estimation of the average treatment effect in one step. Moreover, the multi-pseudo propensity score framework, which is estimated from the diversified balancing net and used for the estimation of the average treatment effect, is presented. Finally, the proposed methods are compared with state-of-the-art methods on three simulation setups and real-world datasets. It has been shown that the proposed self-balancing neural network shows better performance than state-of-the-art methods.

Problem

• Estimating unbiased average treatment effect with confounding variables
• Addressing misspecification risks in propensity score models
• Proposing self-balancing neural network for one-step estimation

Innovation

• Self-balancing neural network estimates treatment effect
• Uses pseudo propensity score from balancing net
• Multi-pseudo propensity score framework improves accuracy