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

by   Rasheed el-Bouri, et al.

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.


page 7

page 8


Preserving Patient Privacy while Training a Predictive Model of In-hospital Mortality

Machine learning models can be used for pattern recognition in medical d...

Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence

A patient's health information is generally fragmented across silos. Tho...

Multi-site fMRI Analysis Using Privacy-preserving Federated Learning and Domain Adaptation: ABIDE Results

Deep learning models have shown their advantage in many different tasks,...

Student-Teacher Curriculum Learning via Reinforcement Learning: Predicting Hospital Inpatient Admission Location

Accurate and reliable prediction of hospital admission location is impor...

Differentially Private Deep Learning with Smooth Sensitivity

Ensuring the privacy of sensitive data used to train modern machine lear...

Federated Uncertainty-Aware Learning for Distributed Hospital EHR Data

Recent works have shown that applying Machine Learning to Electronic Hea...

Pronto: Federated Task Scheduling

We present a federated, asynchronous, memory-limited algorithm for onlin...

Please sign up or login with your details

Forgot password? Click here to reset