Towards Scheduling Federated Deep Learning using Meta-Gradients for Inter-Hospital Learning

TL;DR

This paper introduces a federated learning approach with a meta-gradient trained scheduler and teacher-student framework to train models on sensitive hospital data without compromising privacy, achieving state-of-the-art results.

Contribution

It presents a novel scheduling algorithm using meta-gradients within a federated student-teacher framework for privacy-preserving healthcare data modeling.

Findings

State-of-the-art performance achieved

Effective handling of node poisoning issues

Scheduler enables transfer learning across hospitals

Abstract

Given the abundance and ease of access of personal data today, individual privacy has become of paramount importance, particularly in the healthcare domain. In this work, we aim to utilise patient data extracted from multiple hospital data centres to train a machine learning model without sacrificing patient privacy. We develop a scheduling algorithm in conjunction with a student-teacher algorithm that is deployed in a federated manner. This allows a central model to learn from batches of data at each federal node. The teacher acts between data centres to update the main task (student) algorithm using the data that is stored in the various data centres. We show that the scheduler, trained using meta-gradients, can effectively organise training and as a result train a machine learning model on a diverse dataset without needing explicit access to the patient data. We achieve state-of-the-art performance and show how our method overcomes some of the problems faced in the federated learning such as node poisoning. We further show how the scheduler can be used as a mechanism for transfer learning, allowing different teachers to work together in training a student for state-of-the-art performance.