Learn Electronic Health Records by Fully Decentralized Federated Learning

TL;DR

This paper proposes a fully decentralized federated learning approach for electronic health records that reduces communication rounds significantly while maintaining optimality, demonstrated through large-scale real-world data simulations.

Contribution

It introduces a novel decentralized federated learning algorithm that enhances communication efficiency over graph networks for electronic health records.

Findings

Decentralized federated learning reduces communication rounds.

The method maintains solution optimality.

Superior performance shown on real-world EHR data.

Abstract

Federated learning opens a number of research opportunities due to its high communication efficiency in distributed training problems within a star network. In this paper, we focus on improving the communication efficiency for fully decentralized federated learning over a graph, where the algorithm performs local updates for several iterations and then enables communications among the nodes. In such a way, the communication rounds of exchanging the common interest of parameters can be saved significantly without loss of optimality of the solutions. Multiple numerical simulations based on large, real-world electronic health record databases showcase the superiority of the decentralized federated learning compared with classic methods.