Federated learning for causal inference using deep generative disentangled models

Alejandro Almodóvar, Juan Parras, Santiago Zazo

Keywords: Causal inference, Federated learning, ITE, Treatment effect, Propensity score

TL;DR: An adaptation of Federated Algorithm applied to Causal Inference deep generative models for healthcare scenarios where propensity score changes across processing nodes.

Abstract: In the context of decentralized and privacy-constrained healthcare data settings, we introduce an innovative approach to estimate individual treatment effects (ITE) via federated learning. Emphasizing the critical importance of data privacy in healthcare, especially when drawing on data from various global hospitals, we address challenges arising from data scarcity and specific treatment assignment criteria influenced by the availability of the medication of interest. Our methodology uses federated learning applied to neural network-based generative causal inference models to bridge the gap between decentralized and centralized ITE estimation on a benchmark dataset.

Submission Number: 37