Federated Learning for Causal Inference Using Deep Generative Disentangled Models

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.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Almodóvar et al. "Federated Learning for Causal Inference Using Deep Generative Disentangled Models." NeurIPS 2023 Workshops: DGM4H, 2023.

Markdown

[Almodóvar et al. "Federated Learning for Causal Inference Using Deep Generative Disentangled Models." NeurIPS 2023 Workshops: DGM4H, 2023.](https://mlanthology.org/neuripsw/2023/almodovar2023neuripsw-federated/)

BibTeX

@inproceedings{almodovar2023neuripsw-federated,
  title     = {{Federated Learning for Causal Inference Using Deep Generative Disentangled Models}},
  author    = {Almodóvar, Alejandro and Parras, Juan and Zazo, Santiago},
  booktitle = {NeurIPS 2023 Workshops: DGM4H},
  year      = {2023},
  url       = {https://mlanthology.org/neuripsw/2023/almodovar2023neuripsw-federated/}
}