Communication Efficient Generalized Tensor Factorization for Decentralized Healthcare Networks

TL;DR

This paper introduces CiderTF, a decentralized tensor factorization method that significantly reduces communication costs in healthcare data analysis, enabling privacy-preserving, scalable phenotyping across multiple hospitals.

Contribution

CiderTF is the first decentralized tensor factorization algorithm with four-level communication reduction for healthcare data, enhancing privacy and scalability.

Findings

Achieves up to 99.99% reduction in communication cost.

Maintains comparable convergence to centralized methods.

Effective on real-world EHR datasets.

Abstract

Tensor factorization has been proved as an efficient unsupervised learning approach for health data analysis, especially for computational phenotyping, where the high-dimensional Electronic Health Records (EHRs) with patients' history of medical procedures, medications, diagnosis, lab tests, etc., are converted to meaningful and interpretable medical concepts. Federated tensor factorization distributes the tensor computation to multiple workers under the coordination of a central server, which enables jointly learning the phenotypes across multiple hospitals while preserving the privacy of the patient information. However, existing federated tensor factorization algorithms encounter the single-point-failure issue with the involvement of the central server, which is not only easily exposed to external attacks but also limits the number of clients sharing information with the server under restricted uplink bandwidth. In this paper, we propose CiderTF, a communication-efficient decentralized generalized tensor factorization, which reduces the uplink communication cost by leveraging a four-level communication reduction strategy designed for a generalized tensor factorization, which has the flexibility of modeling different tensor distribution with multiple kinds of loss functions. Experiments on two real-world EHR datasets demonstrate that CiderTF achieves comparable convergence with a communication reduction up to 99.99%.