Distributed Causal Inference using Federated Learning and Bayesian Networks

Abstract

This paper proposes a novel framework for distributed causal inference by integrating federated learning with Bayesian networks. Traditional causal inference methods often require centralized data access, posing significant privacy concerns and logistical challenges, particularly in scenarios involving sensitive data distributed across multiple entities. Our approach addresses this limitation by enabling each participating entity to simultaneously learn causal relationships within its local data using Bayesian networks. These locally learned models are then aggregated to construct a global causal model, mitigating the need for centralized data sharing. We introduce a specific federated learning architecture tailored for causal discovery, incorporating techniques to address confounding and selection bias. The core of the method lies in the iterative refinement of Bayesian network structures through distributed learning, followed by weighted averaging of the learned parameters. We demonstrate the potential of this method through a theoretical analysis, outlining its advantages in terms of privacy preservation, scalability, and robustness. The resulting global causal model provides insights into the underlying causal relationships while respecting data locality. This approach offers a viable pathway for causal inference in distributed, privacy-sensitive environments.